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

    Neuronpedia

    INDEX
    Explanations

    phrases related to certainty or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    words related to assessments or evaluations, particularly regarding actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    currently
    -0.81
    today
    -0.70
     Current
    -0.68
     presently
    -0.68
     currently
    -0.66
    uras
    -0.64
     Currently
    -0.64
    rouse
    -0.63
    veland
    -0.63
    soon
    -0.62
    POSITIVE LOGITS
     intentional
    1.04
    hes
    1.03
     instrumental
    0.96
     careless
    0.94
     mistaken
    0.94
     unintentional
    0.94
     intentionally
    0.91
     originally
    0.90
     negligent
    0.87
     consensual
    0.86
    Act Density 0.447%

    No Known Activations