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

    occurrences of the word "abstract" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    risome
    -0.81
    ICAN
    -0.79
    odder
    -0.76
    UNCH
    -0.72
    omore
    -0.70
    ods
    -0.66
    attering
    -0.64
    hiba
    -0.63
    artney
    -0.62
    unker
    -0.62
    POSITIVE LOGITS
    ions
    1.01
    edly
    0.95
    edIn
    0.92
    stract
    0.90
    furt
    0.84
     algebra
    0.82
    ¥µ
    0.80
    aby
    0.79
    matter
    0.78
     syntax
    0.77
    Act Density 0.012%

    No Known Activations