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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical actions

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate strong actions or changes in state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yond
    -0.59
    been
    -0.58
    hart
    -0.53
    arta
    -0.52
    etric
    -0.52
    thin
    -0.50
    clusive
    -0.48
    ther
    -0.48
    é¾įåĸļ士
    -0.48
    oter
    -0.48
    POSITIVE LOGITS
     tremend
    0.59
     showc
    0.53
    hes
    0.51
    urion
    0.50
     him
    0.49
     quietly
    0.48
     instinctively
    0.48
     himself
    0.48
     summons
    0.47
    otti
    0.47
    Act Density 0.925%

    No Known Activations