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

    Neuronpedia

    INDEX
    Explanations

    the word "Sin" with different variations

    oai_token-act-pair · gpt-3.5-turbo

    references to the film "Sinister" and its related titles or sequels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.81
    enance
    -0.72
     deficits
    -0.67
     principals
    -0.67
    ¶ħ
    -0.65
    eers
    -0.65
    dropping
    -0.64
    ITAL
    -0.61
    ĵĺ
    -0.60
    accompan
    -0.59
    POSITIVE LOGITS
    atra
    1.25
    ners
    1.14
    ned
    1.06
    clair
    1.05
    estro
    1.04
    ews
    1.04
    ister
    0.96
    uous
    0.95
    ew
    0.94
    apore
    0.92
    Act Density 0.036%

    No Known Activations