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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conditional or uncertain situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _COLUMNS
    -0.16
    uin
    -0.15
    oj
    -0.15
     recep
    -0.14
    779
    -0.14
    rál
    -0.14
    पर
    -0.14
     cosm
    -0.14
    oin
    -0.13
    946
    -0.13
    POSITIVE LOGITS
    áºł
    0.15
    é»
    0.15
    νε
    0.14
     Zucker
    0.14
    lob
    0.14
    orda
    0.14
    rides
    0.13
    ÐķС
    0.13
    irl
    0.13
    iek
    0.13
    Act Density 0.115%

    No Known Activations