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

    Neuronpedia

    INDEX
    Explanations

    references to chemical compounds or substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     acer
    -0.71
     convo
    -0.71
     ſever
    -0.68
    gé
    -0.67
     appro
    -0.67
     pleaſure
    -0.67
     myſelf
    -0.66
     enne
    -0.65
     Nek
    -0.65
     kare
    -0.65
    POSITIVE LOGITS
    h
    1.47
    H
    1.46
     H
    1.44
     h
    1.41
    setH
    1.25
    rH
    1.14
    xh
    1.12
    Hh
    1.05
    mh
    0.98
    mH
    0.96
    Act Density 0.143%

    No Known Activations