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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or regulatory matters

    oai_token-act-pair · gpt-3.5-turbo

    references to legal and environmental concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.80
    tions
    -0.66
     predec
    -0.64
    Ô
    -0.64
    pread
    -0.63
    vari
    -0.63
    ãĥĻ
    -0.63
    sbm
    -0.62
     Lv
    -0.61
    compl
    -0.60
    POSITIVE LOGITS
    osphere
    0.92
    ousel
    0.81
    elight
    0.79
    iest
    0.71
     Awakens
    0.70
    liest
    0.70
     cage
    0.69
    crow
    0.68
     itself
    0.67
     canopy
    0.67
    Act Density 0.387%

    No Known Activations