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

    Neuronpedia

    INDEX
    Explanations

    words related to tracking or tracing something back to its origin

    oai_token-act-pair · gpt-3.5-turbo

    terms related to tracing or tracking historical or genealogical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ICES
    -0.75
    anged
    -0.71
    ints
    -0.70
    psey
    -0.70
    vae
    -0.70
    airs
    -0.69
    icum
    -0.67
    bs
    -0.67
    atures
    -0.66
     plurality
    -0.65
    POSITIVE LOGITS
     traced
    1.22
     tracing
    1.08
    xual
    0.83
     Parenthood
    0.83
    heet
    0.76
    ĸļ
    0.71
     bracelet
    0.70
    ioned
    0.64
    ãĥį
    0.63
     weld
    0.62
    Act Density 0.010%

    No Known Activations