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

    Neuronpedia

    INDEX
    Explanations

    terms related to 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
    odder
    -0.77
    risome
    -0.76
    rimp
    -0.70
    attering
    -0.68
    ICAN
    -0.68
    chens
    -0.67
    artney
    -0.67
    owship
    -0.67
    cture
    -0.66
    ogi
    -0.66
    POSITIVE LOGITS
    ions
    1.17
    urally
    0.88
    edly
    0.88
    stract
    0.84
    edIn
    0.80
    ured
    0.80
     syntax
    0.79
     Expression
    0.78
     algebra
    0.78
     painter
    0.77
    Act Density 0.029%

    No Known Activations