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

    Neuronpedia

    INDEX
    Explanations

    comparisons of quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo

    phrases comparing quantities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Eye
    -0.79
    olitan
    -0.69
    pillar
    -0.68
    cu
    -0.68
    YN
    -0.68
     Juda
    -0.68
    ALE
    -0.67
    urther
    -0.66
    aly
    -0.60
    raine
    -0.59
    POSITIVE LOGITS
     usual
    0.90
     average
    0.83
     anticipated
    0.76
    average
    0.76
     expected
    0.76
     ours
    0.74
     advertised
    0.74
     anything
    0.73
     any
    0.71
     theirs
    0.67
    Act Density 0.076%

    No Known Activations