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

    Neuronpedia

    INDEX
    Explanations

    specific keywords related to various news events and topics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Wilson
    -0.94
    OTAL
    -0.89
    FACE
    -0.81
    seeking
    -0.79
     appellant
    -0.79
    berman
    -0.79
    ISON
    -0.78
    pron
    -0.78
    FI
    -0.78
    yahoo
    -0.77
    POSITIVE LOGITS
     accus
    0.88
     Alley
    0.81
     Massacre
    0.79
     rubble
    0.77
    tein
    0.75
    tsy
    0.74
     dolls
    0.74
     poses
    0.73
     flared
    0.72
    mining
    0.72
    Act Density 2.320%

    No Known Activations