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

    Neuronpedia

    INDEX
    Explanations

    different forms of the word "deny" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    denial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.71
    sianic
    -0.61
     CreateTagHelper
    -0.61
    parsedMessage
    -0.60
     CanadaChoose
    -0.60
     AssemblyVersion
    -0.59
    évaluateur
    -0.57
     Lordships
    -0.57
    complexType
    -0.56
    verifyException
    -0.56
    POSITIVE LOGITS
    deny
    0.59
     Deny
    0.57
     deny
    0.57
    Denied
    0.52
    Deny
    0.51
     denial
    0.50
     Denial
    0.50
     denying
    0.47
     denies
    0.47
     Denied
    0.46
    Act Density 0.021%

    No Known Activations