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

    Neuronpedia

    INDEX
    Explanations

    phrases related to promotional language and positive assessments

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    IsContent
    -0.71
    principalTable
    -0.64
    Tikang
    -0.63
    UrlResolution
    -0.62
     विश्वसनीयता
    -0.62
     CURIAM
    -0.62
     estekak
    -0.60
    awtextra
    -0.60
     censiti
    -0.59
    /***/
    -0.59
    POSITIVE LOGITS
    grano
    0.52
     Advancement
    0.47
     apsau
    0.47
     hollow
    0.46
    achal
    0.45
     ghost
    0.43
    nextLine
    0.43
     djur
    0.43
    tivitas
    0.43
     tristesse
    0.43
    Act Density 0.002%

    No Known Activations