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

    Neuronpedia

    INDEX
    Explanations

    the preposition 'of' when followed by a specific number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertodd
    -0.74
    lication
    -0.71
    obyl
    -0.61
    dn
    -0.59
    blance
    -0.58
    itute
    -0.58
    pour
    -0.58
    alez
    -0.57
    assembly
    -0.56
     exting
    -0.56
    POSITIVE LOGITS
     these
    1.04
    these
    1.01
     them
    0.99
     us
    0.96
    them
    0.84
     those
    0.80
     THESE
    0.78
     Cups
    0.77
    ses
    0.75
     THEM
    0.75
    Act Density 0.069%

    No Known Activations