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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons and contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    827
    -0.16
    amp
    -0.16
    ias
    -0.15
    chn
    -0.15
    i
    -0.14
    798
    -0.14
    478
    -0.14
    xing
    -0.13
     looph
    -0.13
    cel
    -0.13
    POSITIVE LOGITS
     ones
    0.19
     others
    0.16
    abbo
    0.15
    edla
    0.15
    ÐIJÑĢÑħÑĸв
    0.15
    regor
    0.15
    egrator
    0.15
    ëĿ½
    0.14
    iyim
    0.14
     usual
    0.14
    Act Density 0.097%

    No Known Activations