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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal opinions or emotions expressed through speech

    oai_token-act-pair · gpt-3.5-turbo

    the end of sentences or statement markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NRS
    -0.64
    ãĥĭ
    -0.63
     Meier
    -0.63
    iden
    -0.63
    iked
    -0.61
     restraining
    -0.61
    IRO
    -0.60
    Winged
    -0.59
    umat
    -0.59
    idious
    -0.58
    POSITIVE LOGITS
    Interstitial
    1.01
    tis
    0.83
    til
    0.78
    emouth
    0.78
    Cause
    0.77
    Mech
    0.75
    nel
    0.75
    taboola
    0.74
    cause
    0.72
    neath
    0.70
    Act Density 0.036%

    No Known Activations