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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey a sense of impact or achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Географија
    -0.38
     masukan
    -0.34
     addition
    -0.34
    namt
    -0.33
     moyens
    -0.33
    izr
    -0.32
     AspNetCore
    -0.31
    žití
    -0.31
     χρή
    -0.31
    롭
    -0.31
    POSITIVE LOGITS
     jackpot
    0.81
    ched
    0.73
     hardest
    0.73
     stride
    0.69
     harder
    0.60
     Jackpot
    0.60
     snag
    0.60
     pause
    0.59
     chords
    0.59
     hard
    0.58
    Act Density 0.210%

    No Known Activations