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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "From" followed by a specific entity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "from" indicating the source of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyde
    -0.82
    SPONSORED
    -0.82
    ifix
    -0.78
    faced
    -0.74
    orkshire
    -0.73
    adian
    -0.72
    ICAN
    -0.72
    aca
    -0.71
    ocene
    -0.70
    isode
    -0.70
    POSITIVE LOGITS
     afar
    1.10
     whence
    1.03
     Wow
    0.85
     Above
    0.80
     thence
    0.79
     Uni
    0.75
     inception
    0.73
     Across
    0.65
     abroad
    0.64
     Carbuncle
    0.63
    Act Density 0.045%

    No Known Activations