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

    Neuronpedia

    INDEX
    Explanations

    instances of cognitive or abstract thought processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otos
    -0.18
    ecycle
    -0.16
    ãģ°
    -0.16
     Fiscal
    -0.15
    loh
    -0.15
    飯
    -0.14
     Ambient
    -0.14
    ssa
    -0.14
    uder
    -0.14
    anio
    -0.14
    POSITIVE LOGITS
    asic
    0.16
    ihn
    0.16
    ipelines
    0.15
    سÙĪب
    0.14
    endum
    0.14
    ãĥ¼ãĥĦ
    0.14
    象
    0.14
    cape
    0.14
    curity
    0.13
    롱
    0.13
    Act Density 0.134%

    No Known Activations