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

    Neuronpedia

    INDEX
    Explanations

    references to patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.44
    <bos>
    -0.40
    riwal
    -0.39
    󠁴
    -0.38
     bä
    -0.33
    fromUtf
    -0.33
     paw
    -0.32
     clasped
    -0.31
    pa
    -0.31
     booklet
    -0.30
    POSITIVE LOGITS
     pat
    1.63
     Pattern
    1.60
    Pattern
    1.55
     pattern
    1.55
    pattern
    1.55
     PAT
    1.50
     Patterns
    1.48
     PATTERN
    1.47
     patterns
    1.45
    patterns
    1.45
    Act Density 0.204%

    No Known Activations