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

    Neuronpedia

    INDEX
    Explanations

    mentions of death and related events in a personal context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     estekak
    -0.49
    LookAnd
    -0.49
    agot
    -0.47
    republik
    -0.46
    rimin
    -0.46
     introduction
    -0.46
    badlogic
    -0.45
    estart
    -0.44
     robo
    -0.43
     agora
    -0.42
    POSITIVE LOGITS
     nahilalakip
    0.81
    GEBURTSDATUM
    0.68
    styleType
    0.68
    CloseOperation
    0.67
     дописавши
    0.67
    soever
    0.65
    UnknownFields
    0.65
     समीक्षाओं
    0.65
    __':
    0.65
     виправивши
    0.65
    Act Density 0.156%

    No Known Activations