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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating warnings or cautions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rof
    -0.15
    enu
    -0.15
    oure
    -0.15
     пан
    -0.15
    ERO
    -0.15
    /Instruction
    -0.14
    è£Ĥ
    -0.14
    åĽ
    -0.14
    .Îł
    -0.14
    .hl
    -0.14
    POSITIVE LOGITS
     unp
    0.16
    lace
    0.16
    dle
    0.15
    pline
    0.14
    odont
    0.14
    unsch
    0.14
     Investigations
    0.13
    chantment
    0.13
     Investigation
    0.13
    unner
    0.13
    Act Density 0.002%

    No Known Activations