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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of something or conditions under which actions occur

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.86
     Monfieur
    -0.72
     Jefus
    -0.70
     againſt
    -0.69
    ſelf
    -0.69
     houſe
    -0.68
     Efq
    -0.68
     pleaſure
    -0.67
     AssemblyCulture
    -0.66
     mergeFrom
    -0.65
    POSITIVE LOGITS
     Without
    1.03
    Without
    0.95
    Ohne
    0.91
     without
    0.91
     regard
    0.90
     a
    0.86
     any
    0.86
    without
    0.86
     WITHOUT
    0.82
    WITHOUT
    0.81
    Act Density 0.087%

    No Known Activations