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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evidence and proof in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    feld
    -0.16
    eson
    -0.15
    ftware
    -0.14
    itler
    -0.14
     ApplicationException
    -0.14
    änger
    -0.13
    632
    -0.13
    INY
    -0.13
    IPA
    -0.13
    andro
    -0.13
    POSITIVE LOGITS
     evidence
    0.55
     proof
    0.50
     Evidence
    0.40
    Evidence
    0.39
     Proof
    0.38
    proof
    0.35
    vidence
    0.35
     supporting
    0.34
     proofs
    0.34
    Proof
    0.34
    Act Density 0.282%

    No Known Activations