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

    Neuronpedia

    INDEX
    Explanations

    references and citations in academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ins
    -0.16
    amera
    -0.16
    ฤษ
    -0.15
    MR
    -0.15
     Echo
    -0.14
     opp
    -0.13
     Stack
    -0.13
    emen
    -0.13
    éĢģ
    -0.13
     Baby
    -0.13
    POSITIVE LOGITS
    ä¸ĺ
    0.18
    idar
    0.18
     Hindered
    0.15
    estro
    0.15
    luv
    0.15
    /Runtime
    0.15
    anager
    0.14
    rei
    0.14
    .Css
    0.14
    riend
    0.14
    Act Density 0.097%

    No Known Activations