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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating past experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -xl
    -0.14
    çļ
    -0.14
    еÑģÑĤÑĮ
    -0.14
    γγ
    -0.14
    adas
    -0.14
    аÑĤкÑĥ
    -0.13
    569
    -0.13
     entrev
    -0.13
    -Men
    -0.13
    vailability
    -0.13
    POSITIVE LOGITS
    afone
    0.17
    opher
    0.16
    okens
    0.15
    lege
    0.15
    come
    0.14
    eria
    0.14
     záp
    0.14
     fwd
    0.14
    京
    0.13
     come
    0.13
    Act Density 0.030%

    No Known Activations