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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and named entities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     M
    -0.58
     T
    -0.57
     F
    -0.56
    F
    -0.53
    D
    -0.52
     D
    -0.50
     p
    -0.50
     K
    -0.50
     E
    -0.50
     L
    -0.49
    POSITIVE LOGITS
    ſelf
    1.22
    Autoritní
    1.22
    transQ
    1.19
     itſelf
    1.13
     neceſſ
    1.11
     Signalez
    1.10
     ſever
    1.09
     raiſ
    1.07
     himſelf
    1.06
     myſelf
    1.06
    Act Density 0.991%

    No Known Activations