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

    Neuronpedia

    INDEX
    Explanations

    references to charitable actions aimed at helping vulnerable populations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     podjela
    -0.58
     كومونز
    -0.57
    URLException
    -0.56
    nsis
    -0.53
    脚注の使い方
    -0.53
     Италијани
    -0.53
     referenties
    -0.52
    TRIBUTE
    -0.52
    oneg
    -0.52
    ussis
    -0.50
    POSITIVE LOGITS
    InstrumentedTest
    0.65
    LLocation
    0.54
     counseling
    0.53
     désolés
    0.52
     contextLoads
    0.50
     shelter
    0.50
    prech
    0.49
     dignidad
    0.49
    currentColor
    0.49
     ajutor
    0.48
    Act Density 0.103%

    No Known Activations