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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong belief or conviction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Protección
    -0.63
     సౌకర్య
    -0.57
    grà
    -0.57
    envoyer
    -0.56
     Jarrett
    -0.56
     Emits
    -0.55
     برانيه
    -0.55
     spreads
    -0.54
     γεν
    -0.54
    styleType
    -0.53
    POSITIVE LOGITS
     Atlantic
    0.91
     convinced
    0.83
     صوتيه
    0.81
    Atlantic
    0.76
     atlantic
    0.74
    hnia
    0.68
     ATLANTIC
    0.67
    RetentionPolicy
    0.64
    hysema
    0.63
     snippetHide
    0.63
    Act Density 0.091%

    No Known Activations