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

    Neuronpedia

    INDEX
    Explanations

    references to laypeople or non-experts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annies
    -0.07
    aria
    -0.07
    TRACE
    -0.07
    ispecies
    -0.06
    arium
    -0.06
    stellung
    -0.06
    coes
    -0.06
    idan
    -0.06
    inia
    -0.06
    icode
    -0.06
    POSITIVE LOGITS
    person
    0.09
    persons
    0.09
    man
    0.08
    men
    0.08
    erson
    0.08
     person
    0.08
    mans
    0.07
     lay
    0.07
    (non
    0.07
    ngo
    0.07
    Act Density 0.002%

    No Known Activations