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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate societal rules or norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    الحياه
    -0.75
     Franks
    -0.68
    riezmann
    -0.65
     fVar
    -0.63
    XmlIgnore
    -0.63
     Irma
    -0.60
     المعيارى
    -0.59
     Bobo
    -0.58
    UrlResolution
    -0.58
     Brody
    -0.58
    POSITIVE LOGITS
     although
    0.76
    although
    0.73
    awtextra
    0.67
     however
    0.63
    however
    0.60
     obwohl
    0.59
     ولك
    0.59
    €“
    0.59
     bulunabilir
    0.59
    ніципалі
    0.57
    Act Density 0.082%

    No Known Activations