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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "After."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kiem
    -0.20
    uki
    -0.14
    ÅĻet
    -0.14
    ковой
    -0.14
    694
    -0.14
    ÑĢажд
    -0.14
    appen
    -0.14
    UFFER
    -0.13
    .infinity
    -0.13
    qui
    -0.13
    POSITIVE LOGITS
    ward
    0.19
    noon
    0.18
    Warn
    0.15
    BOSE
    0.15
    words
    0.15
    ToProps
    0.15
     spending
    0.14
    woods
    0.14
    ạn
    0.14
    maal
    0.14
    Act Density 0.050%

    No Known Activations