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

    Neuronpedia

    INDEX
    Explanations

    phrases related to size and proportion

    oai_token-act-pair · gpt-3.5-turbo

    the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.80
    obo
    -0.78
    TAIN
    -0.76
    imi
    -0.76
    arettes
    -0.75
    arate
    -0.74
    ornia
    -0.74
    arine
    -0.72
    aunder
    -0.71
    udo
    -0.71
    POSITIVE LOGITS
     biggest
    1.20
     sheer
    1.18
     vast
    1.17
     absence
    1.12
     reality
    1.12
     specifics
    1.11
     majority
    1.11
     actual
    1.10
     underlying
    1.09
     presence
    1.08
    Act Density 0.267%

    No Known Activations