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

    Neuronpedia

    INDEX
    Explanations

    expressions of belief and faith

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ar
    -0.74
     SE
    -0.69
     lot
    -0.68
    par
    -0.66
    quad
    -0.66
     N
    -0.65
    SE
    -0.64
     demais
    -0.64
     Gil
    -0.64
    perative
    -0.64
    POSITIVE LOGITS
     BELIEVE
    1.63
     believe
    1.54
    believe
    1.52
     believes
    1.45
     Believe
    1.43
     Belief
    1.43
     Beliefs
    1.43
    Believe
    1.42
     beliefs
    1.38
     believed
    1.38
    Act Density 0.064%

    No Known Activations