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

    Neuronpedia

    INDEX
    Explanations

    references to household items and activities associated with comfort or leisure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppo
    -0.15
    /Foundation
    -0.14
    ocab
    -0.14
    onso
    -0.14
     fragmentation
    -0.13
    byn
    -0.13
     Yine
    -0.13
     Refugee
    -0.13
    TypeDef
    -0.12
     tiener
    -0.12
    POSITIVE LOGITS
    CRET
    0.17
    ugen
    0.16
    æĽľæĹ¥
    0.16
     Hung
    0.16
    .WaitFor
    0.15
    emet
    0.14
    rose
    0.14
    met
    0.14
    óst
    0.14
    egers
    0.14
    Act Density 0.151%

    No Known Activations