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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "symbol" and its variations, indicating a focus on symbolic representations and meanings throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aus
    -0.17
    .AutoScaleMode
    -0.16
    liness
    -0.15
    ิà¸ŀ
    -0.15
    esy
    -0.15
    elier
    -0.15
    amar
    -0.14
    iba
    -0.14
    avors
    -0.14
    lace
    -0.14
    POSITIVE LOGITS
    ically
    0.25
    /sign
    0.19
    lico
    0.18
    ized
    0.17
    izont
    0.17
    izing
    0.17
    -symbol
    0.17
    (Symbol
    0.16
    izes
    0.15
    (symbol
    0.15
    Act Density 0.015%

    No Known Activations