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

    Neuronpedia

    INDEX
    Explanations

    phrases related to new beginnings or introductions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.75
    acebook
    -0.74
    Zip
    -0.70
    osure
    -0.68
    ouse
    -0.67
    veyard
    -0.67
    ashtra
    -0.66
    cius
    -0.65
    aminer
    -0.64
    agree
    -0.63
    POSITIVE LOGITS
    bie
    1.47
    bies
    1.45
     arrivals
    1.22
    foundland
    1.14
     additions
    0.97
     Zealand
    0.96
     entrants
    0.96
     millennium
    0.92
     generation
    0.92
     hires
    0.91
    Act Density 0.463%

    No Known Activations