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

    Neuronpedia

    INDEX
    Explanations

    references to broader contexts or aspects related to specific topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irus
    -0.15
    abby
    -0.15
    itness
    -0.15
    '''č↵
    -0.14
    zl
    -0.14
    olv
    -0.14
     Kw
    -0.14
    tom
    -0.14
    runs
    -0.14
    pawn
    -0.14
    POSITIVE LOGITS
     than
    0.19
    -than
    0.18
    anging
    0.16
    xes
    0.16
    _than
    0.16
    than
    0.15
     ë¡
    0.15
     THAN
    0.15
    thren
    0.14
    */),
    0.14
    Act Density 0.005%

    No Known Activations