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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to claims, evidence, and allegations in discussions of truthfulness and validity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iegel
    -0.16
    oucher
    -0.16
    usted
    -0.15
    xae
    -0.14
    lopedia
    -0.14
    ucc
    -0.14
    azer
    -0.14
    âĻ¥
    -0.14
     neutral
    -0.14
     mocks
    -0.14
    POSITIVE LOGITS
     claim
    0.61
     claims
    0.59
     Claim
    0.54
     Claims
    0.52
     CLAIM
    0.51
    Claim
    0.49
    claims
    0.49
     claimed
    0.48
    claim
    0.48
     claiming
    0.47
    Act Density 0.179%

    No Known Activations