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

    Neuronpedia

    INDEX
    Explanations

    specific locations or positions within a text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "where," particularly in contexts that suggest location or explanation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    0200
    -0.63
    Hunter
    -0.63
    icity
    -0.62
    00000
    -0.62
    Farm
    -0.60
    effects
    -0.60
    nature
    -0.58
     independently
    -0.58
    spell
    -0.58
    994
    -0.57
    POSITIVE LOGITS
    buquerque
    0.84
    ushima
    0.84
    ulic
    0.78
    hov
    0.72
    ioch
    0.71
    atche
    0.69
    anca
    0.68
    icion
    0.66
    haps
    0.65
     Wasserman
    0.64
    Act Density 0.055%

    No Known Activations