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

    Neuronpedia

    INDEX
    Explanations

    instances of observation or witnessing actions involving people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    χε
    -0.65
    //
    -0.65
     Мексичка
    -0.61
    chapper
    -0.58
    eaway
    -0.58
    loses
    -0.58
    aites
    -0.57
    #![
    -0.57
    CLUSIVE
    -0.57
    onner
    -0.55
    POSITIVE LOGITS
    expandindo
    0.66
     '\\;'
    0.61
     للمعارف
    0.60
    tanleria
    0.55
    tagext
    0.54
     noten
    0.53
    "])
    0.52
     vejo
    0.49
     struggle
    0.49
     unfold
    0.49
    Act Density 0.250%

    No Known Activations