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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to a specific group of people or individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the existence or actions of specific groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     roundup
    -0.66
    Ted
    -0.63
     Courier
    -0.63
     Annie
    -0.61
    APD
    -0.60
    Dialog
    -0.59
    vag
    -0.59
    \\\\\\\\
    -0.59
    \/\/
    -0.59
    Lou
    -0.58
    POSITIVE LOGITS
    iris
    0.88
    rir
    0.76
    mol
    0.75
    ãĥīãĥ©
    0.75
     contemplate
    0.72
    esta
    0.70
     oppose
    0.68
    idian
    0.68
    rame
    0.67
     perpetuate
    0.67
    Act Density 0.121%

    No Known Activations