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

    Neuronpedia

    INDEX
    Explanations

    words related to instructions, specific actions, or elements of a document

    oai_token-act-pair · gpt-3.5-turbo

    words related to annotations and their role in information presentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pedigree
    -0.66
    avez
    -0.64
    nas
    -0.63
    porting
    -0.62
    wild
    -0.61
    friends
    -0.60
    bury
    -0.60
    iaz
    -0.60
    library
    -0.60
    bred
    -0.60
    POSITIVE LOGITS
    TION
    1.24
    OGR
    0.84
    luster
    0.81
    ]}
    0.80
    acular
    0.78
    ...]
    0.77
     Frieza
    0.77
    odied
    0.74
    pmwiki
    0.72
    SIZE
    0.71
    Act Density 0.013%

    No Known Activations