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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with events or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    787
    -0.17
    ami
    -0.15
    ester
    -0.15
    »
    -0.15
     Kul
    -0.14
    ानव
    -0.14
    smarty
    -0.14
    63
    -0.14
     Motors
    -0.14
    iales
    -0.14
    POSITIVE LOGITS
    åħ«
    0.19
    29
    0.18
     fif
    0.18
    ®
    0.17
    229
    0.17
    15
    0.17
    Ģ
    0.16
    22
    0.16
     eighth
    0.16
    unts
    0.16
    Act Density 0.013%

    No Known Activations