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

    Neuronpedia

    INDEX
    Explanations

    past participles used with the auxiliary verb 'has'

    oai_token-act-pair · gpt-4-turbo

    verbs indicating the action or state of "taking" something

    oai_token-act-pair · gpt-3.5-turbo

    actions indicating changes or decisions made by organizations or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Manit
    -0.67
    Mp
    -0.65
     taxp
    -0.63
    Old
    -0.62
    Subject
    -0.61
    Mother
    -0.60
    Pic
    -0.60
    lies
    -0.59
     Latter
    -0.59
    Percent
    -0.59
    POSITIVE LOGITS
    phas
    0.81
    been
    0.77
     been
    0.72
    udence
    0.72
    kefeller
    0.71
    avering
    0.70
     Been
    0.69
     enough
    0.68
     knack
    0.68
    angs
    0.68
    Act Density 1.447%

    No Known Activations