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

    Neuronpedia

    INDEX
    Explanations

    phrases concerning environmental damage and moral claims

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     diaria
    -0.45
    뀌
    -0.44
    一次
    -0.42
     Plung
    -0.41
    ']=$
    -0.40
     */}
    -0.40
     entire
    -0.40
     jum
    -0.40
    すべて
    -0.39
    ypes
    -0.39
    POSITIVE LOGITS
     Any
    0.89
    DIPSETTING
    0.82
     Италијани
    0.82
     any
    0.80
     فريبيس
    0.79
    featureID
    0.79
     Italijanski
    0.78
    Any
    0.76
     CreateTagHelper
    0.72
    writeFieldEnd
    0.72
    Act Density 0.086%

    No Known Activations