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

    Neuronpedia

    INDEX
    Explanations

    expressions of belief and skepticism

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

    "believe" or a variation of it

    np_acts-logits-general · gemini-2.0-flash

    believe it or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portail
    -0.68
    SerializedSize
    -0.61
    ar
    -0.59
     uska
    -0.57
    ="">
    -0.57
    utor
    -0.57
    下载附件
    -0.56
    gdx
    -0.56
    IGraphics
    -0.55
    displayquote
    -0.55
    POSITIVE LOGITS
     BELIEVE
    1.15
     Believe
    1.05
    Believe
    1.05
     believe
    1.03
    believe
    1.00
     Beliefs
    0.92
     beliefs
    0.91
     believes
    0.91
     croy
    0.90
     believed
    0.90
    Act Density 0.061%

    No Known Activations