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

    Neuronpedia

    INDEX
    Explanations

    details related to comparisons or contrasts in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assi
    -0.19
    ãģŁãĤī
    -0.17
    yonel
    -0.16
    ijd
    -0.15
    .toolbox
    -0.15
    ãĤĤãģĨ
    -0.14
    iasi
    -0.14
     rotterdam
    -0.14
    antz
    -0.14
    ยม
    -0.14
    POSITIVE LOGITS
     respectively
    0.37
     latter
    0.36
     respective
    0.28
     both
    0.27
     each
    0.26
     former
    0.25
     neither
    0.24
    each
    0.24
    both
    0.24
    Both
    0.23
    Act Density 0.339%

    No Known Activations