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

    Neuronpedia

    INDEX
    Explanations

    phrases related to upright posture or position

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "upright" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pope
    -0.80
    anon
    -0.73
    Berry
    -0.73
    IRO
    -0.73
    775
    -0.72
    URA
    -0.71
     Immunity
    -0.69
    agna
    -0.68
     pains
    -0.68
    ãĤ§
    -0.68
    POSITIVE LOGITS
    İĭ
    1.06
    ensical
    1.00
    ĺħ
    0.92
    ername
    0.90
    xual
    0.89
     imperson
    0.86
    emouth
    0.83
    »Ĵ
    0.83
    ogn
    0.82
    pperc
    0.81
    Act Density 0.013%

    No Known Activations