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

    Neuronpedia

    INDEX
    Explanations

    terms related to comparison between different entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "the rest" or similar phrases indicating a group in contrast to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antha
    -0.64
     Ear
    -0.63
    asma
    -0.63
     Prix
    -0.62
    gee
    -0.61
    interstitial
    -0.60
    Sword
    -0.59
     Rear
    -0.58
    jab
    -0.57
    FK
    -0.56
    POSITIVE LOGITS
    ructure
    1.12
    orative
    1.05
    raint
    0.82
    rike
    0.78
    hetically
    0.77
    erer
    0.77
    rats
    0.76
    lessness
    0.74
    sheets
    0.74
    ricting
    0.73
    Act Density 0.016%

    No Known Activations