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

    Neuronpedia

    INDEX
    Explanations

    words associated with fear or horror

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

    fear and danger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Quid
    -0.54
    Nix
    -0.49
     CFA
    -0.47
     Mitra
    -0.46
     TEE
    -0.46
    pds
    -0.46
     gem
    -0.44
    psum
    -0.44
    MSO
    -0.42
     GEM
    -0.42
    POSITIVE LOGITS
     scary
    1.88
    Scary
    1.80
    scary
    1.73
     Scary
    1.72
     effray
    1.33
     frightening
    1.30
    ariest
    1.28
     terrifying
    1.19
     scares
    1.17
     scaring
    1.09
    Act Density 0.003%

    No Known Activations