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

    Neuronpedia

    INDEX
    Explanations

    expressions of opinion or commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sharp
    -0.15
     Medium
    -0.14
    uil
    -0.14
     Wie
    -0.14
    fk
    -0.14
    SOR
    -0.14
     temper
    -0.14
    RefPtr
    -0.14
     present
    -0.13
    599
    -0.13
    POSITIVE LOGITS
    zdy
    0.18
    ursal
    0.16
    mtree
    0.15
    urse
    0.15
    REEN
    0.15
    udiant
    0.15
    olls
    0.14
    erie
    0.14
    ÄĻż
    0.14
    zug
    0.14
    Act Density 0.044%

    No Known Activations