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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to attitudes and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -1.02
    ̈́
    -1.01
    erequisite
    -0.93
    BeginContext
    -0.93
    uthorized
    -0.91
     Paglinawan
    -0.89
    erequisites
    -0.84
    بوابة
    -0.82
    nocześnie
    -0.80
    Ārējās
    -0.80
    POSITIVE LOGITS
     attitudes
    1.21
     attitude
    1.15
     Attitudes
    1.13
     belief
    0.97
     beliefs
    0.93
    attitude
    0.93
     Attitude
    0.91
     Beliefs
    0.87
     opinions
    0.86
    Attitude
    0.85
    Act Density 0.133%

    No Known Activations