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

    Neuronpedia

    INDEX
    Explanations

    words related to unexpected events or situations that evoke strong emotions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shock."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uties
    -0.75
    allery
    -0.71
    amins
    -0.71
    umbers
    -0.68
     Parenthood
    -0.65
     arrang
    -0.65
     misunder
    -0.64
    ufact
    -0.64
    ittees
    -0.64
    guyen
    -0.63
    POSITIVE LOGITS
    wave
    1.22
    waves
    1.18
     absor
    1.05
    tro
    0.91
    imaru
    0.89
    ingly
    0.83
    crow
    0.83
    er
    0.83
    shock
    0.83
    pson
    0.81
    Act Density 0.025%

    No Known Activations