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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating the act of receiving or obtaining something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or lack of control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    legal
    -0.71
    ilts
    -0.67
    ORS
    -0.65
    abled
    -0.65
    çļ
    -0.64
    burgh
    -0.64
    iets
    -0.64
    Ready
    -0.64
    SUP
    -0.63
    Letter
    -0.62
    POSITIVE LOGITS
     yourself
    0.88
     guys
    0.86
     yourselves
    0.80
     imagine
    0.76
    nikov
    0.71
     gotta
    0.68
    reau
    0.64
     kidding
    0.63
     wonder
    0.63
     sense
    0.63
    Act Density 0.322%

    No Known Activations