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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or justifications related to actions or beliefs

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

    "for" followed by a pronoun or noun

    np_acts-logits-general · gemini-2.0-flash

    for + pronoun/noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.77
    gameserver
    -0.76
     كومونز
    -0.72
    omics
    -0.71
    astéroïdes
    -0.71
    XtraGrid
    -0.70
    Демографія
    -0.67
     Roskov
    -0.66
    opardi
    -0.65
    ⓘ
    -0.65
    POSITIVE LOGITS
     to
    0.73
     someone
    0.69
     people
    0.62
     you
    0.61
     us
    0.61
     others
    0.58
    bootstrapcdn
    0.55
     them
    0.53
     me
    0.52
     somebody
    0.52
    Act Density 0.238%

    No Known Activations