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

    Neuronpedia

    INDEX
    Explanations

    back-to-back patterns

    oai_token-act-pair · gpt-3.5-turbo

    references to sports terminology and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.82
    PF
    -0.78
    Specific
    -0.69
    terms
    -0.67
    Phot
    -0.66
    License
    -0.66
    »Ĵ
    -0.65
    Portland
    -0.65
    hiba
    -0.64
     Located
    -0.62
    POSITIVE LOGITS
     Tide
    0.82
    arching
    0.73
     forth
    0.68
    umbered
    0.65
    kefeller
    0.62
    puff
    0.62
     sofa
    0.61
    eco
    0.60
    forth
    0.60
     sides
    0.59
    Act Density 0.131%

    No Known Activations