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

    Neuronpedia

    INDEX
    Explanations

    important information or statements

    oai_token-act-pair · gpt-3.5-turbo

    statements emphasizing the significance of various issues or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Buyable
    -0.70
    ipes
    -0.63
     Virgin
    -0.62
    Beck
    -0.60
    Fac
    -0.60
     Webster
    -0.60
    isle
    -0.60
    umbs
    -0.60
    é¾
    -0.59
     Viet
    -0.57
    POSITIVE LOGITS
     nonetheless
    0.74
     enough
    0.73
    inet
    0.69
    fort
    0.65
    enberg
    0.64
     nevertheless
    0.63
    inar
    0.62
     Miko
    0.61
    tti
    0.61
     Osw
    0.60
    Act Density 0.077%

    No Known Activations