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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dramatic or sudden actions or events

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of failure or flop

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    APH
    -0.68
     Continuing
    -0.63
    ESS
    -0.61
    CV
    -0.61
     pert
    -0.61
    ript
    -0.60
     vari
    -0.59
     flav
    -0.58
    Detailed
    -0.58
     Visual
    -0.58
    POSITIVE LOGITS
    icycle
    0.86
    ipel
    0.81
    edia
    0.77
    odcast
    0.76
    avorite
    0.76
    ipop
    0.75
    olicy
    0.74
    olitan
    0.74
    dash
    0.71
    ixel
    0.71
    Act Density 0.027%

    No Known Activations