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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence or involvement in scientific measurements or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.18
     *(*
    -0.16
    isÃŃ
    -0.15
    缣
    -0.15
    ExceptionHandler
    -0.15
    MLE
    -0.15
    @qq
    -0.14
     kıs
    -0.14
    isseur
    -0.14
    мÑı
    -0.14
    POSITIVE LOGITS
     conditions
    0.15
     shadow
    0.15
    avad
    0.14
    oyo
    0.14
     enough
    0.14
     reserve
    0.14
    nh
    0.14
    dx
    0.14
    anna
    0.13
     Suzanne
    0.13
    Act Density 0.028%

    No Known Activations