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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     препратки
    -0.79
    aarrggbb
    -0.73
     Autorisations
    -0.72
     betweenstory
    -0.70
    AndEndTag
    -0.70
     screaming
    -0.65
     shouting
    -0.64
    afficheront
    -0.63
    parsedMessage
    -0.62
    TextAppearance
    -0.61
    POSITIVE LOGITS
     paraître
    0.49
    ">:
    0.44
    RetentionPolicy
    0.43
    Réponse
    0.42
     slightly
    0.42
     gaze
    0.42
     stare
    0.41
    ancers
    0.41
     tone
    0.41
    genu
    0.41
    Act Density 0.082%

    No Known Activations