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

    Neuronpedia

    INDEX
    Explanations

    code-related elements and structures in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     importance
    -0.21
     Importance
    -0.20
    redient
    -0.16
    rál
    -0.15
    MP
    -0.15
    _import
    -0.15
    ît
    -0.15
     Narrative
    -0.15
    okane
    -0.14
    import
    -0.14
    POSITIVE LOGITS
    istrovstvÃŃ
    0.19
    asi
    0.18
     len
    0.17
    ensburg
    0.17
    anga
    0.17
    	defer
    0.17
     nil
    0.16
    antis
    0.15
     <-
    0.15
    SSF
    0.15
    Act Density 0.034%

    No Known Activations