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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating persistence and ongoing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    complexContent
    -0.52
     kez
    -0.45
     começar
    -0.44
     Continuous
    -0.44
     mulai
    -0.43
     continuous
    -0.43
     zaczyna
    -0.42
     begyn
    -0.42
     continuing
    -0.41
     Continuing
    -0.41
    POSITIVE LOGITS
     unab
    0.75
    下去
    0.69
     indefinitely
    0.63
    httphttps
    0.58
     uninterrupted
    0.57
     efforts
    0.57
    efforts
    0.56
     momentum
    0.56
     onward
    0.56
     הלא
    0.55
    Act Density 0.152%

    No Known Activations