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

    Neuronpedia

    INDEX
    Explanations

    references to challenges and outcomes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aud
    -0.15
     Fare
    -0.14
     folded
    -0.14
    ivar
    -0.14
    ipt
    -0.13
    hooks
    -0.13
    γÏĩ
    -0.13
     Aud
    -0.13
     att
    -0.13
     conduct
    -0.13
    POSITIVE LOGITS
    etta
    0.16
    703
    0.16
    asa
    0.15
    ripp
    0.14
    avn
    0.14
    uster
    0.14
    ола
    0.14
    -divider
    0.14
     kayn
    0.13
    ứng
    0.13
    Act Density 0.287%

    No Known Activations