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

    Neuronpedia

    INDEX
    Explanations

    reference to statistical or data-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.85
    Autoritní
    -0.77
     Савезне
    -0.76
    )_/¯
    -0.74
    skosten
    -0.72
    uxxxx
    -0.70
    __':
    -0.70
    MLLoader
    -0.68
    NUMX
    -0.67
     distanciation
    -0.66
    POSITIVE LOGITS
    ss
    1.78
    SS
    1.49
    ess
    1.43
     ss
    1.24
    ESS
    1.20
    ass
    1.05
     SS
    1.01
    ssa
    0.96
    sss
    0.95
    ASS
    0.93
    Act Density 2.147%

    No Known Activations