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

    Neuronpedia

    INDEX
    Explanations

    phrases related to improving skills or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Prepositions followed by articles or possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    on, of preposition pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arşivlendi
    -0.66
    UserScript
    -0.56
    +#+#
    -0.56
     CURIAM
    -0.56
     bezeichneter
    -0.55
     AssemblyCompany
    -0.55
     propOrder
    -0.53
    -0.52
    ésult
    -0.52
     <<<<<<<<<<<<<<
    -0.52
    POSITIVE LOGITS
     Anderson
    0.52
    ocratic
    0.50
    alum
    0.46
     Anders
    0.46
     recent
    0.46
     Edwards
    0.45
     the
    0.45
    titud
    0.45
    the
    0.45
     Ralph
    0.44
    Act Density 1.024%

    No Known Activations