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

    Neuronpedia

    INDEX
    Explanations

    syntactical structures or symbols associated with code snippets or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pent
    -0.17
    sher
    -0.16
    erokee
    -0.16
    inger
    -0.15
    chemas
    -0.15
    Us
    -0.14
    'l
    -0.14
    athers
    -0.14
    935
    -0.14
     Us
    -0.14
    POSITIVE LOGITS
    indow
    0.15
     McCabe
    0.14
    ynom
    0.14
    žen
    0.14
     Owen
    0.14
    onds
    0.13
    axter
    0.13
    CHAIN
    0.13
    accent
    0.13
    orphism
    0.13
    Act Density 0.009%

    No Known Activations