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

    Neuronpedia

    INDEX
    Explanations

    figures related to statistics or data analysis

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chenko
    -0.89
    oslav
    -0.78
    nikov
    -0.76
    zona
    -0.74
    mare
    -0.74
    kie
    -0.72
    hus
    -0.72
    quartered
    -0.71
    forge
    -0.71
    roach
    -0.70
    POSITIVE LOGITS
     purposes
    1.05
    gery
    1.02
    bidden
    0.98
     instance
    0.95
    geries
    0.93
     sale
    0.91
     each
    0.91
     example
    0.84
    aging
    0.83
     starters
    0.82
    Act Density 0.206%

    No Known Activations