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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms (words ending with 's)

    oai_token-act-pair · gpt-3.5-turbo

    direct quotations or speech in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.74
     Meier
    -0.70
     Ducks
    -0.69
     Archangel
    -0.66
    ensen
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.63
     blow
    -0.63
    idious
    -0.60
    acket
    -0.60
    itol
    -0.59
    POSITIVE LOGITS
    Interstitial
    1.27
    taboola
    1.15
    MpServer
    0.93
    Mech
    0.92
    Cause
    0.90
    tis
    0.88
    cause
    0.83
    uminium
    0.74
     ',
    0.73
    SIGN
    0.72
    Act Density 0.095%

    No Known Activations