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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific names occurring in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was" indicating past actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ennett
    -0.62
    rers
    -0.62
    ants
    -0.62
    antics
    -0.61
    Footnote
    -0.61
     [+]
    -0.60
    otic
    -0.59
    entric
    -0.59
    zynski
    -0.59
     IMAGES
    -0.58
    POSITIVE LOGITS
     originally
    1.13
     formerly
    1.10
    hes
    1.08
     previously
    1.02
    wolves
    0.94
     supposed
    0.91
     conceived
    0.89
     initially
    0.89
     instrumental
    0.84
     destined
    0.80
    Act Density 0.170%

    No Known Activations