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

    Neuronpedia

    INDEX
    Explanations

    words related to impact or success, particularly in a positive sense

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hit" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĢ
    -0.67
    idge
    -0.66
    UTH
    -0.63
    inent
    -0.63
    ignty
    -0.63
    çĶŁ
    -0.62
    agin
    -0.62
    uth
    -0.60
    aer
    -0.59
    eur
    -0.59
    POSITIVE LOGITS
    ched
    1.42
    ches
    1.06
     puberty
    0.98
    boxes
    0.94
     hardest
    0.91
     rock
    0.83
    ropolis
    0.82
    usalem
    0.79
     harder
    0.79
    achi
    0.78
    Act Density 0.031%

    No Known Activations