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

    Neuronpedia

    INDEX
    Explanations

    the conjunction "or."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.08
    2:0.08
    3:0.06
    4:0.08
    5:0.08
    6:0.07
    7:0.08
    8:0.08
    9:0.08
    10:0.09
    11:0.09
    Negative Logits
     typew
    -2.99
     extr
    -2.88
     editing
    -2.82
     transcription
    -2.76
     typed
    -2.73
     typing
    -2.67
     mRNA
    -2.61
     peripheral
    -2.46
     archaeological
    -2.45
     sermon
    -2.44
    POSITIVE LOGITS
    worst
    3.40
    apest
    3.17
    omsday
    2.98
    oos
    2.77
     bans
    2.70
    rament
    2.69
    lando
    2.63
    Boost
    2.61
    otin
    2.61
    abis
    2.60
    Act Density 0.000%

    No Known Activations