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

    Neuronpedia

    INDEX
    Explanations

    actions and their outcomes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andon
    -0.16
    ollapsed
    -0.16
    òi
    -0.15
    łí
    -0.15
    itol
    -0.15
    _GENERIC
    -0.14
     "%"
    -0.14
    Pipe
    -0.14
    acr
    -0.14
    iscard
    -0.14
    POSITIVE LOGITS
     Ortiz
    0.16
    _framework
    0.16
    _hooks
    0.14
     رÙħ
    0.14
     Zap
    0.14
    ITCH
    0.14
    ulis
    0.14
    emoc
    0.14
    frau
    0.14
    -hooks
    0.14
    Act Density 0.012%

    No Known Activations