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

    Neuronpedia

    INDEX
    Explanations

    phrases related to belief or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    expressions of belief or conviction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conservancy
    -0.77
    ague
    -0.69
    agher
    -0.67
    cloth
    -0.66
    mentioned
    -0.66
    apeake
    -0.65
    nec
    -0.65
    practice
    -0.64
    aucas
    -0.64
    aste
    -0.63
    POSITIVE LOGITS
    ieve
    0.80
    fulness
    0.78
     believe
    0.74
    rill
    0.74
     believes
    0.72
    phas
    0.72
    orean
    0.71
    ership
    0.70
     believing
    0.70
     BEL
    0.70
    Act Density 0.040%

    No Known Activations