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

    Neuronpedia

    INDEX
    Explanations

    instances where something is considered problematic or controversial

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to disagreement or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.73
    ioned
    -0.73
    icter
    -0.72
     exting
    -0.68
    weeney
    -0.68
    wich
    -0.67
    hei
    -0.66
    wake
    -0.66
    ocene
    -0.64
    ewater
    -0.64
    POSITIVE LOGITS
     nor
    0.93
     anybody
    0.92
     anyone
    0.80
     anymore
    0.73
     either
    0.72
     anything
    0.70
     Explorer
    0.67
     enjoyment
    0.65
     or
    0.64
     temptation
    0.63
    Act Density 0.275%

    No Known Activations