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

    Neuronpedia

    INDEX
    Explanations

    words related to the horror genre

    oai_token-act-pair · gpt-3.5-turbo

    references to the horror genre

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UTC
    -0.87
    cial
    -0.76
    ETS
    -0.73
    cius
    -0.71
    eting
    -0.71
    ets
    -0.69
    adal
    -0.68
    PAC
    -0.67
     assigned
    -0.67
    ça
    -0.67
    POSITIVE LOGITS
     horror
    3.60
     Horror
    2.69
     horrors
    2.08
     Lovecraft
    1.72
     horr
    1.55
     terror
    1.54
     gore
    1.50
     horrifying
    1.45
     fright
    1.44
     horrified
    1.42
    Act Density 0.017%

    No Known Activations