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

    Neuronpedia

    INDEX
    Explanations

    verbs related to cognitive processes and abilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to recognition, perception, and memory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    legates
    -0.74
    backer
    -0.73
     incentiv
    -0.65
    ortium
    -0.64
    Thumbnail
    -0.64
    GBT
    -0.64
    ammy
    -0.63
    wage
    -0.63
     flagship
    -0.62
    xus
    -0.62
    POSITIVE LOGITS
     cues
    0.95
     stimuli
    0.94
     objects
    0.88
     instinctively
    0.84
     whats
    0.83
     aloud
    0.82
     correctly
    0.82
    ibly
    0.81
     distances
    0.79
     accurately
    0.75
    Act Density 0.349%

    No Known Activations