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

    Neuronpedia

    INDEX
    Explanations

    references to horror-related themes and elements in writing

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

    horror stories and movies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sam
    -0.49
     sam
    -0.47
     Sam
    -0.47
    SAM
    -0.46
     Twee
    -0.46
     SAM
    -0.45
    Ap
    -0.44
    Samuel
    -0.44
    Pipe
    -0.44
    Am
    -0.44
    POSITIVE LOGITS
     horror
    2.03
    horror
    1.94
     Horror
    1.91
    Horror
    1.83
     horrors
    1.30
     horrified
    0.98
     HOR
    0.87
     horri
    0.87
     horrifying
    0.86
     Horowitz
    0.85
    Act Density 0.004%

    No Known Activations