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

    Neuronpedia

    INDEX
    Explanations

    technical specifications related to electronic devices and their performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lengths
    -0.16
     sprink
    -0.14
    bane
    -0.14
    aviour
    -0.14
    teness
    -0.14
    ivery
    -0.14
    Length
    -0.14
    vé
    -0.14
     minLength
    -0.13
    ообÑĢаз
    -0.13
    POSITIVE LOGITS
     power
    0.38
    power
    0.33
     capacity
    0.33
    -power
    0.32
     rated
    0.32
     output
    0.32
     rating
    0.31
    -rated
    0.30
     POWER
    0.29
     моÑī
    0.29
    Act Density 0.142%

    No Known Activations