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

    Neuronpedia

    INDEX
    Explanations

    phrases related to frequency or repetition of events or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     majority
    -0.15
     aliqua
    -0.15
     largest
    -0.14
    ungi
    -0.14
     TWO
    -0.14
    ocaly
    -0.14
    three
    -0.14
    uars
    -0.14
     three
    -0.13
    saldo
    -0.13
    POSITIVE LOGITS
     thousand
    0.60
     thousands
    0.54
     hundred
    0.53
     hundreds
    0.52
     countless
    0.50
     million
    0.45
     Hundreds
    0.44
     dozens
    0.44
     Thousand
    0.43
    åįĥ
    0.43
    Act Density 0.247%

    No Known Activations