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

    Neuronpedia

    INDEX
    Explanations

    uses of specific methods or techniques

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "using."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owship
    -0.78
    brother
    -0.71
    uberty
    -0.70
    hood
    -0.66
    stal
    -0.66
    witz
    -0.65
    naire
    -0.63
    present
    -0.62
    nesty
    -0.61
    lah
    -0.60
    POSITIVE LOGITS
    FUL
    0.87
    iences
    0.79
     computers
    0.77
     techniques
    0.74
     shortcuts
    0.73
     tools
    0.69
     contacts
    0.69
    ience
    0.69
     technologies
    0.68
     needles
    0.67
    Act Density 0.047%

    No Known Activations