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

    Neuronpedia

    INDEX
    Explanations

    numerical values and symbols in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.79
     face
    -0.56
     ro
    -0.56
     flight
    -0.55
    ="";
    -0.54
     Mid
    -0.54
     —
    -0.54
     over
    -0.53
    #%%
    -0.53
     T
    -0.52
    POSITIVE LOGITS
     myſelf
    1.07
     uſed
    0.99
     itſelf
    0.99
     himſelf
    0.97
     marseille
    0.93
     doubtnut
    0.91
     deſt
    0.91
     Monfieur
    0.91
     auffi
    0.90
     themſelves
    0.89
    Act Density 0.322%

    No Known Activations