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

    Neuronpedia

    INDEX
    Explanations

    instances of expression and representation of sentiment or public opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ordinate
    -0.15
    _uploaded
    -0.15
     Lust
    -0.14
    ero
    -0.14
     Zusammen
    -0.14
    QRS
    -0.14
    irma
    -0.14
     Zaman
    -0.14
    ãĥ³ãĤº
    -0.13
    (Is
    -0.13
    POSITIVE LOGITS
     behalf
    0.27
     everyone
    0.25
     everybody
    0.23
     myself
    0.20
     sentiments
    0.19
    everyone
    0.19
     Everyone
    0.19
    Everyone
    0.18
     millions
    0.16
    人人
    0.15
    Act Density 0.110%

    No Known Activations