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
    nam
    -0.17
     Bias
    -0.15
    ç±į
    -0.14
    erte
    -0.13
    439
    -0.13
    519
    -0.13
    654
    -0.13
     hardly
    -0.13
    ilha
    -0.13
    agas
    -0.13
    POSITIVE LOGITS
    icipants
    0.16
    loquent
    0.15
    fuck
    0.15
    erosis
    0.15
    olarity
    0.14
    ispens
    0.14
    enment
    0.14
     Bun
    0.14
     bdsm
    0.13
    ValueCollection
    0.13
    Act Density 0.000%

    No Known Activations