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

    Neuronpedia

    INDEX
    Explanations

    verbs related to taking action or following instructions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "you have" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usp
    -0.70
    peed
    -0.67
    Discuss
    -0.65
    inance
    -0.65
    cession
    -0.64
    Else
    -0.63
    hyde
    -0.63
    icy
    -0.59
    wi
    -0.59
    ima
    -0.58
    POSITIVE LOGITS
     gotta
    1.03
     yourself
    0.93
     probably
    0.93
     heard
    0.90
     guessed
    0.88
     choices
    0.82
     undoubtedly
    0.82
     doubtless
    0.82
     seen
    0.81
     yourselves
    0.80
    Act Density 0.081%

    No Known Activations