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

    Neuronpedia

    INDEX
    Explanations

    instances of null or false values, indicating uninitialized or erroneous states in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vel
    -0.16
    zug
    -0.16
     dziew
    -0.15
    irsch
    -0.15
    óż
    -0.14
    interop
    -0.14
    ERIC
    -0.14
    庫
    -0.14
    lush
    -0.14
    ftar
    -0.14
    POSITIVE LOGITS
     Griff
    0.15
    åŀ
    0.15
    alias
    0.15
    ÃĹ↵↵
    0.15
    iken
    0.15
    ission
    0.15
     alias
    0.14
     peppers
    0.14
    _alias
    0.14
     Griffin
    0.14
    Act Density 0.080%

    No Known Activations