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

    Neuronpedia

    INDEX
    Explanations

    verbs related to movement or action

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     objects
    -0.76
     documents
    -0.74
     timelines
    -0.73
     branches
    -0.72
     assemblies
    -0.71
     chambers
    -0.70
     pools
    -0.69
     channels
    -0.68
     districts
    -0.68
     rooms
    -0.68
    POSITIVE LOGITS
     apiece
    0.88
    few
    0.73
    joy
    0.72
    dozen
    0.71
    coat
    0.70
    zyk
    0.70
    atical
    0.68
    igmatic
    0.68
    pour
    0.68
    phrase
    0.68
    Act Density 0.300%

    No Known Activations