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

    Neuronpedia

    INDEX
    Explanations

    words related to movement or action

    oai_token-act-pair · gpt-3.5-turbo

    words related to movement or actions, particularly in contexts of influx or flow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CHR
    -0.60
     hereafter
    -0.60
     proced
    -0.60
    ä¸ī
    -0.60
    PRES
    -0.59
     Salvation
    -0.59
     preserving
    -0.58
    ACTED
    -0.57
     Wo
    -0.56
     fairness
    -0.56
    POSITIVE LOGITS
    aughs
    0.88
    uating
    0.72
    etooth
    0.72
    idation
    0.69
    idity
    0.66
    puff
    0.66
    ishing
    0.65
     toilets
    0.65
    pees
    0.65
    olia
    0.65
    Act Density 0.100%

    No Known Activations