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

    Neuronpedia

    INDEX
    Explanations

    questions or statements directed towards the reader

    oai_token-act-pair · gpt-3.5-turbo

    questions directed at the reader that encourage engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    currently
    -0.71
    Maker
    -0.71
    anon
    -0.67
    rette
    -0.66
    arget
    -0.65
    objects
    -0.65
    renheit
    -0.65
    assemb
    -0.64
    ilus
    -0.64
    Member
    -0.64
    POSITIVE LOGITS
     stumble
    0.77
     lapse
    0.73
    arcity
    0.72
     looph
    0.72
     omission
    0.71
     earlier
    0.70
     foresee
    0.70
    ACP
    0.69
     last
    0.69
     bailed
    0.69
    Act Density 0.244%

    No Known Activations