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

    Neuronpedia

    INDEX
    Explanations

    the word "regardless"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditions or exceptions regardless of certain factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ischer
    -0.72
    lyak
    -0.72
    arie
    -0.72
    ANS
    -0.70
    ards
    -0.69
    resa
    -0.68
    icide
    -0.66
    ahime
    -0.66
    okane
    -0.66
    atis
    -0.65
    POSITIVE LOGITS
     circumstance
    0.86
    stellar
    0.81
     whatsoever
    0.80
     jurisdiction
    0.78
     course
    0.76
     sheer
    0.73
     circumstances
    0.73
     geography
    0.71
     whether
    0.70
     spe
    0.70
    Act Density 0.045%

    No Known Activations