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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    subjects related to notable individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Catal
    -0.84
     å¤
    -0.84
     indo
    -0.82
     legitim
    -0.82
     Yar
    -0.80
     Sar
    -0.77
     Marian
    -0.75
     transc
    -0.75
     BAS
    -0.74
     Alph
    -0.73
    POSITIVE LOGITS
    ick
    1.72
    icks
    1.55
    itt
    1.45
    ICK
    1.45
    igg
    1.28
    ickers
    1.27
    icker
    1.25
    ipp
    1.23
    ock
    1.22
    ott
    1.22
    Act Density 0.194%

    No Known Activations