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

    Neuronpedia

    INDEX
    Explanations

    instructions or guidance on how to perform specific actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve learning or teaching specific skills or knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    女
    -0.66
    icipated
    -0.64
    threat
    -0.63
    idon
    -0.62
    aden
    -0.60
    rued
    -0.60
    outed
    -0.59
    Rum
    -0.57
    idan
    -0.57
    975
    -0.57
    POSITIVE LOGITS
     to
    0.99
     much
    0.89
    itzer
    0.88
     easy
    0.81
    much
    0.79
     TO
    0.75
    to
    0.75
     else
    0.71
     To
    0.69
    TO
    0.68
    Act Density 0.074%

    No Known Activations