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

    Neuronpedia

    INDEX
    Explanations

    expressions of fear or terror

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    fear and terror

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.77
    +#+#
    -0.73
    expandindo
    -0.70
    GEBURTSDATUM
    -0.64
    MigrationBuilder
    -0.63
     ivelany
    -0.62
    majánló
    -0.62
     հղումներ
    -0.60
     الحره
    -0.59
    adaptiveStyles
    -0.59
    POSITIVE LOGITS
     terrifying
    1.30
     terrified
    1.12
     horrifying
    0.87
    rifying
    0.78
     frightening
    0.78
     frightened
    0.63
     terri
    0.63
     horrified
    0.62
    rified
    0.58
     frighten
    0.55
    Act Density 0.007%

    No Known Activations