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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or events that occur

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "arise" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sho
    -0.71
    ney
    -0.69
    phis
    -0.69
    edo
    -0.65
    awks
    -0.64
    opers
    -0.63
    ogun
    -0.63
    ingham
    -0.62
    jab
    -0.60
     tape
    -0.59
    POSITIVE LOGITS
     arising
    0.95
     spontaneously
    0.94
     arises
    0.86
     anew
    0.85
     arise
    0.81
    nces
    0.79
    rences
    0.78
     arose
    0.78
     arisen
    0.77
    DragonMagazine
    0.69
    Act Density 0.029%

    No Known Activations