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

    Neuronpedia

    INDEX
    Explanations

    comparisons indicating proximity or distance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating proximity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wa
    -0.70
    ford
    -0.64
    yr
    -0.63
    elson
    -0.63
    draft
    -0.62
    å°
    -0.62
    anta
    -0.62
    WI
    -0.61
    don
    -0.61
    onomy
    -0.60
    POSITIVE LOGITS
    enough
    0.78
     enough
    0.76
     satisfactory
    0.74
     resembling
    0.73
    ittees
    0.70
     anymore
    0.69
     nor
    0.69
    Enough
    0.68
     adequate
    0.68
     Enough
    0.67
    Act Density 0.071%

    No Known Activations