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

    Neuronpedia

    INDEX
    Explanations

    references to historical events and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ariel
    -0.15
    abyrin
    -0.15
    ORMAT
    -0.15
    .ua
    -0.15
    raphics
    -0.14
    óa
    -0.14
    enment
    -0.14
    cq
    -0.13
    vue
    -0.13
    IFn
    -0.13
    POSITIVE LOGITS
     Roman
    0.42
     Rome
    0.38
    Roman
    0.38
     Romans
    0.33
     Pompe
    0.32
     roman
    0.32
     Caesar
    0.29
     Forum
    0.28
     Roma
    0.28
    Forum
    0.28
    Act Density 0.183%

    No Known Activations