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

    Neuronpedia

    INDEX
    Explanations

    references to sexual abuse and exploitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    //{{
    -0.18
    μβ
    -0.17
    uder
    -0.16
    quo
    -0.16
    anders
    -0.15
    iteDatabase
    -0.15
    laden
    -0.15
    lean
    -0.14
     Defensive
    -0.14
     Freder
    -0.14
    POSITIVE LOGITS
    rve
    0.18
     Schultz
    0.16
     grounds
    0.15
    vier
    0.14
    orio
    0.14
    grounds
    0.14
    enda
    0.14
    ahun
    0.13
     Imag
    0.13
    opper
    0.13
    Act Density 0.024%

    No Known Activations