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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and references to family relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pristupljeno
    -0.61
    ValueStyle
    -0.59
    gives
    -0.54
    bians
    -0.52
    utación
    -0.52
    berra
    -0.52
    umoj
    -0.52
    becue
    -0.51
    __':
    -0.50
    ciful
    -0.50
    POSITIVE LOGITS
     überhaupt
    0.62
     Chwiliwch
    0.57
     ogóle
    0.54
    ActionCreators
    0.54
     вообще
    0.51
    basicConfig
    0.50
     esiste
    0.47
     existent
    0.47
     esistono
    0.46
     esist
    0.46
    Act Density 0.123%

    No Known Activations