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

    Neuronpedia

    INDEX
    Explanations

    phrases related to curves and diagrams

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    alling
    -0.82
    raq
    -0.81
    alez
    -0.81
    emonic
    -0.78
    axy
    -0.77
    oran
    -0.75
    rament
    -0.75
    anmar
    -0.73
    ific
    -0.72
    uments
    -0.72
    POSITIVE LOGITS
     Jenner
    0.76
    bent
    0.73
     Osc
    0.72
     Sturgeon
    0.69
    ting
    0.65
    mint
    0.64
     Sisters
    0.63
    balls
    0.63
     Marble
    0.62
    ogue
    0.61
    Act Density 0.060%

    No Known Activations