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

    Neuronpedia

    INDEX
    Explanations

    statements expressing opinions or feelings about specific events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their occurrences in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     crocod
    -1.00
     choking
    -0.92
     modelling
    -0.88
     brid
    -0.88
     contingency
    -0.87
     velvet
    -0.86
     ape
    -0.84
     emb
    -0.84
     asbestos
    -0.82
     Tarant
    -0.82
    POSITIVE LOGITS
    âĹı
    1.52
    Ļ
    1.51
    âĺ
    1.31
    ãĥ©ãĥ³
    1.30
    Gil
    1.28
    ãģĵ
    1.27
    ç¥ŀ
    1.27
    ï
    1.27
    ãĥ¡
    1.27
    Loading
    1.26
    Act Density 0.123%

    No Known Activations