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

    Neuronpedia

    INDEX
    Explanations

    statements regarding the presence or absence of evidence to support claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.55
     houſe
    -0.54
     purpoſe
    -0.53
     diſt
    -0.49
    ſelf
    -0.47
     ſtate
    -0.47
    ChildScrollView
    -0.47
     occafion
    -0.46
    хьтан
    -0.45
     ftate
    -0.45
    POSITIVE LOGITS
     evidence
    0.89
     proof
    0.86
    evidence
    0.74
     Evidence
    0.72
    证据
    0.71
     preuves
    0.70
     proofs
    0.69
    Evidence
    0.68
     Proof
    0.68
     preuve
    0.67
    Act Density 1.163%

    No Known Activations