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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data analysis or calculation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "using" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owship
    -0.77
    uberty
    -0.75
    nesty
    -0.70
    hood
    -0.68
    brother
    -0.68
    witz
    -0.67
    cffffcc
    -0.66
    hound
    -0.64
    naire
    -0.64
     4090
    -0.64
    POSITIVE LOGITS
    FUL
    0.83
    iences
    0.78
     contacts
    0.76
     techniques
    0.72
     computers
    0.71
     combinations
    0.70
     scissors
    0.69
     tools
    0.69
    fully
    0.68
     leverage
    0.68
    Act Density 0.046%

    No Known Activations