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

    Neuronpedia

    INDEX
    Explanations

    references to real-life experiences and personal stories

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.76
    UnknownFieldSet
    -0.76
    ArrowToggle
    -0.63
    StoreMessageInfo
    -0.63
    Sprintf
    -0.60
     StringTokenizer
    -0.60
    脚注の使い方
    -0.59
    Personensuche
    -0.59
     referenties
    -0.58
     发表于
    -0.57
    POSITIVE LOGITS
     real
    0.82
    现实
    0.68
     реаль
    0.66
    real
    0.65
     réel
    0.65
     reales
    0.60
     IRL
    0.59
    現實
    0.59
    REAL
    0.57
     actual
    0.55
    Act Density 0.186%

    No Known Activations