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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various issues or topics being discussed

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the presence of problems or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.79
    Contents
    -0.77
    odes
    -0.75
    aren
    -0.70
    Explore
    -0.68
    chairs
    -0.66
    soever
    -0.66
     guiActiveUnfocused
    -0.65
    ids
    -0.65
    COMPLE
    -0.63
    POSITIVE LOGITS
     Matter
    0.70
     obligatory
    0.66
     Lav
    0.65
     kicker
    0.64
     Butt
    0.63
     Glac
    0.63
     Mail
    0.61
     Huma
    0.60
     the
    0.60
     Tatt
    0.60
    Act Density 0.143%

    No Known Activations