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

    Neuronpedia

    INDEX
    Explanations

    names of entities or individuals, particularly in legal or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     KP
    -0.63
     K
    -0.62
     KD
    -0.61
    RefNanny
    -0.61
     KC
    -0.57
    æder
    -0.56
    KP
    -0.56
    KC
    -0.54
    Kc
    -0.54
     Dove
    -0.54
    POSITIVE LOGITS
     Sark
    0.91
    ARK
    0.90
    Hk
    0.89
    ark
    0.88
     ARK
    0.87
    Tk
    0.87
    Mk
    0.86
    trk
    0.85
    Ck
    0.85
    brk
    0.85
    Act Density 0.835%

    No Known Activations