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

    Neuronpedia

    INDEX
    Explanations

    conditional clauses that express hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ela
    -0.16
    ãĥ¼ãĤº
    -0.15
    implify
    -0.15
     sink
    -0.15
    aphore
    -0.15
    urdy
    -0.15
    iu
    -0.14
    lev
    -0.14
     Sherman
    -0.14
    stro
    -0.14
    POSITIVE LOGITS
    209
    0.16
    asis
    0.16
    ltk
    0.15
    Ïģί
    0.15
    agate
    0.14
     Celt
    0.14
    å¸
    0.13
    596
    0.13
    FY
    0.13
    缩
    0.13
    Act Density 0.045%

    No Known Activations