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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or near-certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey frequency or prevalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö
    -0.74
    ocratic
    -0.69
    ר
    -0.68
    oted
    -0.68
     brim
    -0.68
    è¦ļéĨĴ
    -0.67
     à¤
    -0.66
    eding
    -0.66
     messenger
    -0.65
    æѦ
    -0.65
    POSITIVE LOGITS
    ths
    0.83
    ogether
    0.83
    Berry
    0.78
    terson
    0.76
    urion
    0.73
     Enough
    0.72
     Says
    0.72
    irteen
    0.71
    irds
    0.70
     Benefits
    0.70
    Act Density 0.009%

    No Known Activations