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

    Neuronpedia

    INDEX
    Explanations

    the word "of" followed by possessive pronouns or determiners

    oai_token-act-pair · gpt-3.5-turbo

    phrases referencing the concept of size or proportion related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )].
    -0.76
    aire
    -0.75
    Enlarge
    -0.73
    KK
    -0.70
    far
    -0.69
    umerable
    -0.69
    claim
    -0.69
    orie
    -0.68
    hra
    -0.67
    hran
    -0.65
    POSITIVE LOGITS
     veins
    0.73
     our
    0.72
     each
    0.71
     planets
    0.71
     these
    0.70
     Nanto
    0.69
     your
    0.69
     the
    0.69
     those
    0.67
     atoms
    0.67
    Act Density 0.164%

    No Known Activations