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

    Neuronpedia

    INDEX
    Explanations

    commands and functions related to game and programming contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +#+
    -0.95
     Efq
    -0.89
    ########.
    -0.88
     greateſt
    -0.83
    InvalidProtocol
    -0.81
    enterOuterAlt
    -0.81
     myſelf
    -0.78
     Diſ
    -0.76
    addContainerGap
    -0.76
     occaf
    -0.75
    POSITIVE LOGITS
    ,
    0.58
     im
    0.50
    -
    0.50
     i
    0.50
     and
    0.50
     a
    0.49
     Y
    0.48
     bar
    0.48
     the
    0.48
     und
    0.47
    Act Density 0.052%

    No Known Activations