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

    Neuronpedia

    INDEX
    Explanations

    specific references to entities, including organizations and proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    149
    -0.15
     gan
    -0.15
     den
    -0.14
    524
    -0.13
     instead
    -0.13
    iko
    -0.13
     reasonably
    -0.13
     vis
    -0.13
    etta
    -0.13
    ãģĹãģ
    -0.13
    POSITIVE LOGITS
    SCRI
    0.18
    enet
    0.15
    olid
    0.14
    isay
    0.14
    bens
    0.14
    ãĤ¯ãĥŃ
    0.14
    keh
    0.14
    mgr
    0.14
    ummings
    0.14
    tings
    0.13
    Act Density 0.040%

    No Known Activations