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

    Neuronpedia

    INDEX
    Explanations

    words related to various forms of the word "form"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to form or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prints
    -0.76
    print
    -0.72
    lder
    -0.67
    animate
    -0.65
    built
    -0.64
     Maya
    -0.62
    holder
    -0.62
    ching
    -0.62
    FORM
    -0.61
     frag
    -0.60
    POSITIVE LOGITS
    etheus
    1.01
    ammu
    0.96
    orph
    0.95
    itory
    0.91
    agher
    0.88
    ancy
    0.88
    ont
    0.87
    s
    0.87
    sg
    0.87
    aic
    0.86
    Act Density 0.016%

    No Known Activations