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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating sources or origins of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     from
    -0.20
     assisted
    -0.17
     next
    -0.16
     settlement
    -0.16
     once
    -0.16
    kla
    -0.15
     under
    -0.15
     guard
    -0.14
    ongs
    -0.14
     no
    -0.14
    POSITIVE LOGITS
    niž
    0.16
    -parse
    0.15
    oksen
    0.15
    CID
    0.15
    OSC
    0.15
    IDEO
    0.15
    /inet
    0.15
    ksen
    0.14
    าà¸ĩ
    0.14
    741
    0.14
    Act Density 0.039%

    No Known Activations