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

    Neuronpedia

    INDEX
    Explanations

    titles of songs and albums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :
    -0.56
    -
    -0.55
    ,
    -0.53
     quaisquer
    -0.52
    @
    -0.47
    =
    -0.47
     coû
    -0.46
    ://
    -0.46
     essas
    -0.45
     duração
    -0.45
    POSITIVE LOGITS
     itſelf
    0.86
    ſelf
    0.81
     myſelf
    0.81
    ſelves
    0.80
    CloseOperation
    0.77
     Riproduzione
    0.76
     faſt
    0.75
     ARXIV
    0.73
     Reſ
    0.71
     pleaſure
    0.71
    Act Density 0.228%

    No Known Activations