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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    references to specific actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mbuds
    -0.69
    zi
    -0.68
    ILE
    -0.63
    ondo
    -0.63
    used
    -0.62
    ringe
    -0.61
    inately
    -0.61
    OV
    -0.60
    awk
    -0.60
    ruciating
    -0.60
    POSITIVE LOGITS
     actions
    1.16
    uations
    1.07
     ACTIONS
    1.00
     action
    0.92
     Actions
    0.83
    uation
    0.82
    igraph
    0.80
    terday
    0.79
    bucks
    0.79
    uality
    0.78
    Act Density 0.015%

    No Known Activations