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

    Neuronpedia

    INDEX
    Explanations

    phrases related to detailed information or specifics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to details and disclosures about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    retty
    -0.78
    à¼
    -0.74
    example
    -0.73
    ulla
    -0.72
    archy
    -0.71
    OGR
    -0.70
    rack
    -0.69
    ulo
    -0.69
    =]
    -0.68
    à©
    -0.67
    POSITIVE LOGITS
     how
    1.27
     whereabouts
    1.21
     upcoming
    1.07
     why
    1.01
     impending
    0.90
     what
    0.85
     whether
    0.84
     future
    0.83
     forthcoming
    0.83
     preparations
    0.81
    Act Density 0.171%

    No Known Activations