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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions and decisions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    quartered
    -0.70
    oplan
    -0.68
    oway
    -0.63
    antis
    -0.59
     formerly
    -0.59
     currently
    -0.59
    ilty
    -0.58
     Native
    -0.58
    DN
    -0.58
    forming
    -0.58
    POSITIVE LOGITS
     proceeded
    0.93
     recons
    0.85
     abruptly
    0.85
     disappears
    0.79
     laun
    0.74
     helicop
    0.74
     realize
    0.73
     realized
    0.72
     prest
    0.72
     forg
    0.72
    Act Density 0.213%

    No Known Activations