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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news events and information

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    IDS
    -1.08
    EStream
    -1.07
    rir
    -1.02
    atro
    -1.02
    hyde
    -1.00
    aminer
    -0.98
    ackle
    -0.92
    abwe
    -0.91
    izont
    -0.90
     Schwe
    -0.89
    POSITIVE LOGITS
    ocating
    1.86
    ocate
    1.72
    iance
    1.72
    ocated
    1.72
    ocation
    1.72
    iances
    1.71
    owing
    1.64
    igator
    1.57
    usions
    1.53
    ocations
    1.48
    Act Density 1.798%

    No Known Activations