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

    Neuronpedia

    INDEX
    Explanations

    terms related to fear and horror

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    excellents
    -0.52
     Anspruch
    -0.51
     Ansprüche
    -0.49
    odzi
    -0.48
     Indul
    -0.47
     reclama
    -0.46
    bub
    -0.46
     syns
    -0.45
    foly
    -0.44
     Tears
    -0.44
    POSITIVE LOGITS
     frighten
    1.43
     scare
    1.40
     scary
    1.38
     scared
    1.38
     frightening
    1.36
     frightened
    1.36
     fright
    1.33
     scaring
    1.32
    Scary
    1.32
    Scared
    1.32
    Act Density 0.237%

    No Known Activations