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

    Neuronpedia

    INDEX
    Explanations

    names containing the suffix "-ist"

    oai_token-act-pair · gpt-3.5-turbo

    words related to artistry or creative professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.83
    accompanied
    -0.81
    BOX
    -0.71
     smoot
    -0.71
    ilings
    -0.67
    Dub
    -0.63
    perty
    -0.63
    WT
    -0.61
    ãģ®éŃĶ
    -0.60
     Strait
    -0.59
    POSITIVE LOGITS
    orical
    0.93
    ribution
    0.92
    otle
    0.84
    ophe
    0.84
    opol
    0.83
    ribute
    0.83
    ribut
    0.83
    ocrat
    0.83
    ocene
    0.81
    ess
    0.77
    Act Density 0.033%

    No Known Activations