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

    Neuronpedia

    INDEX
    Explanations

    symbols and textual representations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "eff" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prus
    -0.71
    doctor
    -0.71
     Bans
    -0.70
    olan
    -0.70
     Kai
    -0.69
    ulia
    -0.68
    ran
    -0.67
    asus
    -0.67
    orkshire
    -0.67
    yssey
    -0.66
    POSITIVE LOGITS
     eff
    3.78
     Eff
    2.43
    eff
    2.17
     EFF
    2.08
    EFF
    1.68
     diff
    0.98
     effic
    0.91
     aff
    0.91
     fec
    0.90
     perf
    0.88
    Act Density 0.043%

    No Known Activations