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

    Neuronpedia

    INDEX
    Explanations

    words related to conditional statements or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rego
    -0.15
    βα
    -0.14
     Hour
    -0.14
    ATTR
    -0.14
    FLOW
    -0.14
     Furn
    -0.14
    sah
    -0.13
     Ut
    -0.13
    osten
    -0.13
    ethnic
    -0.13
    POSITIVE LOGITS
    917
    0.17
    709
    0.16
    ãģĹãĤĩãģĨ
    0.15
    atcher
    0.15
    omo
    0.15
    éry
    0.14
    emm
    0.14
    enko
    0.14
    acie
    0.14
    ufe
    0.14
    Act Density 0.012%

    No Known Activations