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

    Neuronpedia

    INDEX
    Explanations

    references to group size or collective nouns related to populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yat
    -0.16
    erge
    -0.15
    olla
    -0.15
    echn
    -0.15
    á»ĩu
    -0.15
     Lover
    -0.15
    urer
    -0.15
    ileri
    -0.15
    ategories
    -0.14
    TargetException
    -0.14
    POSITIVE LOGITS
    usion
    0.15
    EEK
    0.14
     propag
    0.14
    çĦ¶
    0.14
    YTE
    0.14
    loat
    0.14
    icht
    0.13
    ì°©
    0.13
     Kirk
    0.13
    mans
    0.13
    Act Density 0.010%

    No Known Activations