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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases about commitment and support

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

    "We" followed by a verb expressing sentiment

    np_acts-logits-general · gemini-2.0-flash

    expressing positive sentiment and future outlook

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -1.01
    脚注の使い方
    -0.90
    :✨
    -0.73
    لينكات
    -0.73
    shafen
    -0.71
    Externé
    -0.71
    -0.69
    లాలు
    -0.69
    aarrggbb
    -0.69
    󠁣
    -0.68
    POSITIVE LOGITS
     hope
    1.09
     hopes
    0.93
     thank
    0.88
     welcome
    0.86
     expect
    0.84
     believe
    0.83
     intend
    0.78
    hope
    0.76
     applaud
    0.75
     congratulate
    0.75
    Act Density 0.229%

    No Known Activations