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

    Neuronpedia

    INDEX
    Explanations

    concepts related to familial connections and historical significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ober
    -0.16
    iclass
    -0.14
    urum
    -0.14
    ìĨĶ
    -0.14
     -------------------------------------------------------------------------
    -0.14
    emics
    -0.13
     ocas
    -0.13
    upos
    -0.13
    ASF
    -0.13
    olec
    -0.13
    POSITIVE LOGITS
     instead
    0.26
     otherwise
    0.23
    Otherwise
    0.23
     вмеÑģÑĤ
    0.22
     Otherwise
    0.22
    instead
    0.20
     Instead
    0.20
     OTHERWISE
    0.19
     responsible
    0.19
    Instead
    0.19
    Act Density 0.025%

    No Known Activations