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

    Neuronpedia

    INDEX
    Explanations

    expressions of belief and conviction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lot
    -0.72
    ar
    -0.72
     SE
    -0.70
    par
    -0.68
    個
    -0.67
    SE
    -0.65
    quad
    -0.65
    morris
    -0.64
     N
    -0.64
    por
    -0.64
    POSITIVE LOGITS
     BELIEVE
    1.59
     Beliefs
    1.47
     believe
    1.47
    believe
    1.47
     Belief
    1.43
     beliefs
    1.42
     believes
    1.41
    Belief
    1.35
     believed
    1.35
     Believe
    1.34
    Act Density 0.055%

    No Known Activations