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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    significant and impactful concepts or facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.88
    ighed
    -0.88
    anwhile
    -0.81
    externalActionCode
    -0.80
    ully
    -0.77
    hower
    -0.77
     Aware
    -0.76
    apo
    -0.74
    ensibly
    -0.73
    ylum
    -0.72
    POSITIVE LOGITS
     examples
    0.99
     contenders
    0.97
     things
    0.93
     moments
    0.93
     ideas
    0.92
     roles
    0.91
     instances
    0.89
     scenarios
    0.89
     situations
    0.88
     cases
    0.88
    Act Density 0.327%

    No Known Activations