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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific references to people, places, or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    depending
    -0.45
    IBLE
    -0.44
    natureconservancy
    -0.41
    Cooldown
    -0.40
    ITNESS
    -0.39
    edIn
    -0.39
    FontSize
    -0.39
    laughs
    -0.39
    ©¶æ¥µ
    -0.36
    unless
    -0.36
    POSITIVE LOGITS
     and
    1.38
     &
    1.12
     AND
    1.00
    and
    0.87
     etc
    0.79
     et
    0.77
    &
    0.69
     or
    0.68
    -,
    0.67
    And
    0.64
    Act Density 2.681%

    No Known Activations