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

    Neuronpedia

    INDEX
    Explanations

    relationships among characters in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uÅŁ
    -0.17
    еÑī
    -0.16
     Impro
    -0.15
    ôle
    -0.14
    opoly
    -0.14
     impro
    -0.14
    datagrid
    -0.14
    elman
    -0.14
    lsx
    -0.13
    ël
    -0.13
    POSITIVE LOGITS
    arith
    0.15
     actionTypes
    0.14
    chal
    0.14
     Chall
    0.14
     Animalia
    0.14
    AtPath
    0.14
    رÛĮÙħ
    0.14
     Phaser
    0.13
    .LOG
    0.13
    ruary
    0.13
    Act Density 0.014%

    No Known Activations