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

    Neuronpedia

    INDEX
    Explanations

    words related to abstention or abstaining

    oai_token-act-pair · gpt-3.5-turbo

    terms related to abstention and abstinence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.76
     Tycoon
    -0.71
    ORGE
    -0.70
    NetMessage
    -0.69
     Hastings
    -0.68
     Kinnikuman
    -0.66
     Sisters
    -0.66
     Pioneer
    -0.66
    eways
    -0.65
     Stevens
    -0.65
    POSITIVE LOGITS
     abst
    1.40
    iencies
    0.93
    ention
    0.85
    aye
    0.81
     scrut
    0.77
    inent
    0.75
     minded
    0.74
    cheat
    0.72
    arians
    0.71
    inently
    0.70
    Act Density 0.005%

    No Known Activations