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

    Neuronpedia

    INDEX
    Explanations

    phrases that highlight significant or noteworthy occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    outil
    -0.16
    YD
    -0.15
    odal
    -0.14
    ç¯
    -0.14
     itself
    -0.14
    меÑĤÑĮ
    -0.14
    those
    -0.14
     lẫn
    -0.13
    ãĥ³ãĥĦ
    -0.13
    enders
    -0.13
    POSITIVE LOGITS
    curity
    0.25
    cond
    0.24
    quence
    0.24
     sorts
    0.24
     days
    0.24
     kinds
    0.23
     guys
    0.21
     types
    0.20
    quential
    0.19
     two
    0.19
    Act Density 0.125%

    No Known Activations