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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating interaction or engagement with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PIO
    -0.20
    urat
    -0.17
    .Uri
    -0.17
    ãĤ¤ãĤº
    -0.16
    .sul
    -0.16
    amework
    -0.16
    견
    -0.16
    lico
    -0.16
    lon
    -0.15
    getc
    -0.15
    POSITIVE LOGITS
    A
    0.15
    EC
    0.15
    ror
    0.15
    ue
    0.15
    noticed
    0.15
    els
    0.14
    409
    0.14
    ustr
    0.14
    obj
    0.14
    HQ
    0.14
    Act Density 0.025%

    No Known Activations