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

    Neuronpedia

    INDEX
    Explanations

    references to digital object identifiers (DOIs) in citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mock
    -0.15
    elia
    -0.15
    -ms
    -0.14
    )((((
    -0.14
    stra
    -0.14
    zar
    -0.14
    och
    -0.14
     Anc
    -0.14
    _cover
    -0.14
    éri
    -0.14
    POSITIVE LOGITS
    .org
    0.18
     justice
    0.15
     Exc
    0.15
    iday
    0.15
     exc
    0.14
    ì¸
    0.14
    Forge
    0.14
    hatt
    0.14
     Sang
    0.14
    andal
    0.13
    Act Density 0.008%

    No Known Activations