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

    Neuronpedia

    INDEX
    Explanations

    things related to scientific concepts and research

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    olicy
    -0.82
    rue
    -0.79
    irms
    -0.74
    axies
    -0.73
    obile
    -0.73
    arten
    -0.72
    erest
    -0.71
    estern
    -0.71
    eor
    -0.69
    eve
    -0.67
    POSITIVE LOGITS
    chard
    0.99
     alternatively
    0.93
    ifice
    0.92
    chid
    0.86
    acle
    0.82
    acles
    0.82
    chest
    0.76
     equivalent
    0.74
    ific
    0.74
    GAN
    0.73
    Act Density 0.065%

    No Known Activations