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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software commands or technical processes

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to data, system operations, and software commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĹ¼
    -0.71
    EStreamFrame
    -0.67
    é¾įå¥ij士
    -0.66
    azy
    -0.65
    zac
    -0.65
    externalActionCode
    -0.64
    Interstitial
    -0.64
    Cola
    -0.64
    POSE
    -0.63
    Poly
    -0.62
    POSITIVE LOGITS
     consists
    1.15
     comprises
    1.08
     consisted
    1.06
     is
    0.98
     continues
    0.96
     contains
    0.96
     has
    0.96
     was
    0.93
     extends
    0.92
     provides
    0.91
    Act Density 0.559%

    No Known Activations