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

    Neuronpedia

    INDEX
    Explanations

    references to policies and related conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayi
    -0.15
    affle
    -0.15
    oad
    -0.15
    intro
    -0.14
    erin
    -0.14
    بÙĬÙĨ
    -0.13
    addError
    -0.13
    _TURN
    -0.13
    acf
    -0.13
    .Cryptography
    -0.13
    POSITIVE LOGITS
     guaranteed
    0.21
     guarantees
    0.19
     direct
    0.19
     Direct
    0.18
     Guaranteed
    0.18
    Direct
    0.17
     promise
    0.17
     guarantee
    0.17
     START
    0.17
     starter
    0.17
    Act Density 0.024%

    No Known Activations