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

    Neuronpedia

    INDEX
    Explanations

    instances of specific words related to measurement or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illage
    -0.17
    .nasa
    -0.16
    DN
    -0.16
    cles
    -0.15
     inde
    -0.14
    ida
    -0.14
    atively
    -0.14
    ative
    -0.14
    amente
    -0.14
    azu
    -0.14
    POSITIVE LOGITS
    phins
    0.17
     Dw
    0.17
    dw
    0.17
    fault
    0.15
    anzi
    0.15
    raid
    0.14
    _WAKE
    0.14
    sett
    0.14
    .dw
    0.14
    çĵ
    0.14
    Act Density 0.017%

    No Known Activations