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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers or lists related to performance or efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     such
    -0.21
     (),
    -0.16
    )<
    -0.16
    esc
    -0.16
     sc
    -0.15
     r
    -0.15
     like
    -0.15
     w
    -0.15
     bas
    -0.15
    –
    -0.15
    POSITIVE LOGITS
    0.32
    0.16
     ë²Ī
    0.16
    à§į
    0.15
    mult
    0.15
    ppard
    0.15
    eight
    0.15
    herits
    0.15
    athe
    0.15
    Mult
    0.15
    Act Density 0.042%

    No Known Activations