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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal and contractual obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WARDED
    -0.14
     first
    -0.14
    epar
    -0.14
    ãĤĬ
    -0.14
    isse
    -0.14
    ello
    -0.13
    ader
    -0.13
    ibold
    -0.13
    æĭ¼
    -0.13
    acao
    -0.13
    POSITIVE LOGITS
    elfth
    0.22
     第
    0.19
    第
    0.18
    ième
    0.17
    entieth
    0.16
    edik
    0.16
    ÑģÑıÑĤ
    0.16
    degree
    0.16
    avanaugh
    0.16
     degree
    0.15
    Act Density 0.044%

    No Known Activations