Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    keywords related to tools, policies, applications, figures, recipes, videos, principles, questions, tricks, treaties, cultures, events, libraries, locations, patterns, experiences, scars, experiments, and emails

    oai_token-act-pair · gpt-3.5-turbo

    references to tools, policies, and various forms of media or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Operation
    -0.67
    ©¶æ
    -0.63
    ties
    -0.61
    iann
    -0.59
     Surviv
    -0.58
    abet
    -0.58
     paramedics
    -0.57
    renheit
    -0.57
    OSP
    -0.57
     Azerb
    -0.56
    POSITIVE LOGITS
     alike
    1.69
     thereof
    1.19
     respectively
    1.09
     thereto
    0.96
     therein
    0.91
    hips
    0.90
     accordingly
    0.89
    mith
    0.88
    hare
    0.84
    paces
    0.81
    Act Density 0.255%

    No Known Activations