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

    Neuronpedia

    INDEX
    Explanations

    instances of conjunctions, particularly the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    тва
    -0.50
    The
    -0.49
     iste
    -0.48
     kise
    -0.48
     kra
    -0.47
    戚
    -0.47
     kis
    -0.47
    ис
    -0.46
     esca
    -0.46
     starter
    -0.46
    POSITIVE LOGITS
    LookAnd
    0.92
     يتيمه
    0.82
    RRect
    0.80
    JspWriter
    0.79
    efeated
    0.79
     Efq
    0.78
    ReusableCell
    0.77
    󠁢
    0.77
    TargetException
    0.76
     autorytatywna
    0.75
    Act Density 0.202%

    No Known Activations