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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a range of data or entries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouve
    -0.07
    yonel
    -0.07
    ÑģÑĤÑĢÑĥкÑĤоÑĢ
    -0.07
    adele
    -0.07
     клад
    -0.07
    inear
    -0.07
    .locals
    -0.07
    éĻµ
    -0.06
    ording
    -0.06
    ustr
    -0.06
    POSITIVE LOGITS
    OKIE
    0.08
    ledi
    0.06
    è¯ļ
    0.06
     sw
    0.06
     ap
    0.06
     gon
    0.06
    hints
    0.06
     Overrides
    0.06
    asta
    0.06
    rech
    0.06
    Act Density 0.000%

    No Known Activations