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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events and actions in past tense

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    unless
    -0.82
    ahime
    -0.69
    %.
    -0.67
    except
    -0.67
    WF
    -0.67
    .}
    -0.66
    ©¶æ¥µ
    -0.65
     unless
    -0.64
    bys
    -0.63
    ansk
    -0.62
    POSITIVE LOGITS
     last
    0.70
     hes
    0.60
     parting
    0.58
     announcing
    0.53
     landfall
    0.53
     puberty
    0.52
     inquire
    0.52
     timeout
    0.51
     finally
    0.51
     final
    0.51
    Act Density 0.344%

    No Known Activations