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

    Neuronpedia

    INDEX
    Explanations

    expressions of clarity and certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rey
    -0.16
    OTH
    -0.15
    ighth
    -0.15
    áln
    -0.15
    mpi
    -0.15
    achts
    -0.14
    ht
    -0.14
    tok
    -0.14
    çŃĭ
    -0.14
    wort
    -0.14
    POSITIVE LOGITS
     obvious
    0.15
    Gesture
    0.14
    aram
    0.14
     è½
    0.13
    061
    0.13
     continent
    0.13
    estro
    0.13
    meno
    0.13
     mean
    0.13
    urgeon
    0.13
    Act Density 0.217%

    No Known Activations