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

    Neuronpedia

    INDEX
    Explanations

    expressions of collective responsibility or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allery
    -0.07
     Heller
    -0.07
    352
    -0.07
    lops
    -0.07
     pts
    -0.06
    lak
    -0.06
    aroo
    -0.06
     blinds
    -0.06
    ROP
    -0.06
    .addHandler
    -0.06
    POSITIVE LOGITS
     guess
    0.08
    uw
    0.06
    tdown
    0.06
    itable
    0.06
     spoiler
    0.06
     else
    0.06
    rowable
    0.06
    guess
    0.06
    ìłķ
    0.06
     Guide
    0.06
    Act Density 0.003%

    No Known Activations