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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts or ideas

    oai_token-act-pair · gpt-3.5-turbo

    references to abstract concepts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    risome
    -0.84
    ICAN
    -0.76
    odder
    -0.74
    UNCH
    -0.72
    omore
    -0.70
    attering
    -0.68
    unker
    -0.67
    ogi
    -0.67
    asts
    -0.66
    artney
    -0.66
    POSITIVE LOGITS
    ions
    1.14
    stract
    0.93
    edly
    0.88
    matter
    0.85
     algebra
    0.84
    edIn
    0.82
     abstract
    0.80
     syntax
    0.77
    urally
    0.76
     painter
    0.76
    Act Density 0.018%

    No Known Activations