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

    Neuronpedia

    INDEX
    Explanations

    words indicating that something is too extreme, intense, or unsuitable in some way

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate something is "too" or beyond a certain threshold

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    qi
    -0.76
     Accessed
    -0.74
    LM
    -0.73
    ipple
    -0.72
    deen
    -0.71
    provided
    -0.71
    nex
    -0.70
    loo
    -0.70
    doi
    -0.70
    chenko
    -0.69
    POSITIVE LOGITS
    geries
    0.96
     experimentation
    0.87
     comparison
    0.83
     purposes
    0.79
     us
    0.77
     sustained
    0.76
    gery
    0.75
     comparisons
    0.73
     inclusion
    0.73
     optimum
    0.71
    Act Density 0.152%

    No Known Activations