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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote institutional affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angu
    -0.18
    pector
    -0.15
    γγ
    -0.15
    ainter
    -0.15
    acer
    -0.14
    itore
    -0.14
    ì§Ģëħ¸
    -0.14
    AIT
    -0.14
    æ´
    -0.14
    ién
    -0.14
    POSITIVE LOGITS
    rien
    0.15
    eczy
    0.14
    ended
    0.14
     Nutzung
    0.14
    endum
    0.14
    vor
    0.14
    odes
    0.13
    ub
    0.13
    icht
    0.13
     élect
    0.13
    Act Density 0.052%

    No Known Activations