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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "patterns" and its variations, indicating a focus on the identification and discussion of recurring themes or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ath
    -0.16
    orners
    -0.15
     onAnimation
    -0.15
    inet
    -0.15
    ldr
    -0.15
    کتر
    -0.14
    holm
    -0.14
    peater
    -0.14
    eros
    -0.14
    elo
    -0.14
    POSITIVE LOGITS
    (pattern
    0.23
    -pattern
    0.21
    .pattern
    0.21
     pattern
    0.20
     patterns
    0.20
     Pattern
    0.19
     Patterns
    0.19
    pattern
    0.19
    patterns
    0.17
    ed
    0.17
    Act Density 0.021%

    No Known Activations