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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate statistics and probabilities related to betting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achen
    -0.15
    Ñģклад
    -0.15
    enville
    -0.15
    =edge
    -0.14
    Expose
    -0.14
    amar
    -0.14
    erness
    -0.14
    tres
    -0.13
     eg
    -0.13
    ¯¯
    -0.13
    POSITIVE LOGITS
     Circular
    0.18
    STALL
    0.16
    alli
    0.16
    allas
    0.16
    jeta
    0.15
    olas
    0.15
    ĺħ
    0.14
     půj
    0.14
    duk
    0.14
     Hust
    0.14
    Act Density 0.005%

    No Known Activations