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

    Neuronpedia

    INDEX
    Explanations

    comparisons or differences

    oai_token-act-pair · gpt-3.5-turbo

    the special end-of-text token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prod
    -0.60
     banner
    -0.57
    SPONSORED
    -0.54
     emblem
    -0.54
     Plaza
    -0.54
     Abbey
    -0.53
     Santana
    -0.53
     Fowler
    -0.53
     searches
    -0.52
     Corrections
    -0.52
    POSITIVE LOGITS
    etheless
    1.06
    lihood
    1.00
    tenance
    1.00
    usterity
    0.94
    terday
    0.91
    vised
    0.88
    mosp
    0.84
    ãĤ´ãĥ³
    0.84
    vern
    0.83
    -$
    0.83
    Act Density 0.107%

    No Known Activations