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

    Neuronpedia

    INDEX
    Explanations

    identifiers or references to specific actions, states, or entities in diverse contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hen
    -0.15
    STA
    -0.14
    yc
    -0.14
    fty
    -0.14
     Fleet
    -0.14
    hari
    -0.13
    adows
    -0.13
    Stamp
    -0.13
    ngth
    -0.13
    ided
    -0.13
    POSITIVE LOGITS
    avia
    0.17
    bjerg
    0.15
     rub
    0.15
     Gib
    0.14
     Rub
    0.14
    Rub
    0.14
    872
    0.14
    наÑĤ
    0.14
    .nasa
    0.14
    .cp
    0.14
    Act Density 0.003%

    No Known Activations