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

    Neuronpedia

    INDEX
    Explanations

    keywords and technical terms associated with data and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wing
    -0.16
    abase
    -0.16
    637
    -0.15
     Abrams
    -0.15
    pton
    -0.15
    metric
    -0.14
    PT
    -0.14
    wap
    -0.14
    ante
    -0.14
    onis
    -0.14
    POSITIVE LOGITS
    esto
    0.19
    ÅĤad
    0.16
    Ĥæķ°
    0.15
    olis
    0.15
    Ñıз
    0.15
    chyb
    0.14
    anth
    0.14
    CEE
    0.14
    otte
    0.14
    Ŀå§ĭ
    0.14
    Act Density 0.011%

    No Known Activations