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

    Neuronpedia

    INDEX
    Explanations

    repetition of the word "more" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.99
    /**
    -0.97
    AutoScaleMode
    -0.81
     pleaſure
    -0.81
     HasFactory
    -0.80
     Majefty
    -0.79
     houſe
    -0.78
     purpoſe
    -0.75
     Monfieur
    -0.75
    bufio
    -0.73
    POSITIVE LOGITS
     more
    4.07
    more
    3.19
     More
    2.93
    More
    2.88
     MORE
    2.81
    MORE
    2.41
     mehr
    2.34
     lebih
    2.27
     más
    2.16
     более
    2.09
    Act Density 0.153%

    No Known Activations