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

    Neuronpedia

    INDEX
    Explanations

    phrases related to abilities or skills

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of abilities or capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bride
    -0.70
    arer
    -0.68
     Schwe
    -0.68
     Parents
    -0.66
     Surv
    -0.66
    ModLoader
    -0.64
    algia
    -0.64
    gone
    -0.62
     Deer
    -0.62
    article
    -0.62
    POSITIVE LOGITS
    Reviewer
    1.05
    ibility
    0.87
    Ability
    0.83
    ibilities
    0.82
    bodied
    0.82
     manipulate
    0.80
    ologies
    0.73
     to
    0.73
    ioned
    0.72
    isphere
    0.71
    Act Density 0.057%

    No Known Activations