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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating the possibility or inevitability of negative outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -0.74
     betweenstory
    -0.69
    featureID
    -0.68
    PreferredItem
    -0.67
     nakalista
    -0.63
     ainfi
    -0.62
     ujednoznacz
    -0.61
     Италијани
    -0.60
     tartalomajánló
    -0.58
     Administrativna
    -0.57
    POSITIVE LOGITS
     tetap
    0.55
     sekal
    0.50
    still
    0.43
     still
    0.42
     ändå
    0.41
     comunque
    0.40
     trotzdem
    0.40
     Dennoch
    0.38
    Still
    0.37
    それでも
    0.37
    Act Density 0.381%

    No Known Activations