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

    Neuronpedia

    INDEX
    Explanations

    actions and states related to outcomes and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utz
    -0.17
    osten
    -0.15
    uÄį
    -0.15
    dden
    -0.15
    agher
    -0.14
    rente
    -0.14
    otts
    -0.14
    955
    -0.14
    inand
    -0.14
    ncoder
    -0.14
    POSITIVE LOGITS
    of
    0.24
    OF
    0.23
     Of
    0.23
    Of
    0.23
    _Of
    0.22
    -of
    0.21
    	of
    0.20
     OF
    0.18
    .of
    0.18
    _of
    0.18
    Act Density 0.144%

    No Known Activations