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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code-related syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     catch
    -0.48
    äum
    -0.47
     throw
    -0.47
     contributo
    -0.46
    ieties
    -0.46
    ivir
    -0.45
    Stones
    -0.44
     Throw
    -0.43
     sit
    -0.43
    XmlAccessType
    -0.43
    POSITIVE LOGITS
     saves
    0.89
     washes
    0.85
     burns
    0.84
     draws
    0.82
     restores
    0.81
    Saves
    0.81
     kills
    0.80
     selects
    0.80
     Saves
    0.80
     withdraws
    0.79
    Act Density 0.325%

    No Known Activations