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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the number of stories in a building

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DED
    -0.15
    amina
    -0.15
    CCA
    -0.15
    isle
    -0.14
    ilib
    -0.14
    unda
    -0.14
    ¯¯
    -0.14
    .communication
    -0.14
    иÑģÑĤÑĢа
    -0.14
    ria
    -0.13
    POSITIVE LOGITS
    ColumnInfo
    0.17
     Prospect
    0.16
     Depths
    0.15
    BOR
    0.14
    cache
    0.14
    à¤Ĩर
    0.14
    ache
    0.14
    LabelText
    0.14
    649
    0.13
    otel
    0.13
    Act Density 0.008%

    No Known Activations