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

    Neuronpedia

    INDEX
    Explanations

    instances of empty string representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     déliv
    -0.43
     étan
    -0.42
     dễ
    -0.40
     perfeitamente
    -0.40
     desconhe
    -0.40
     perfeito
    -0.39
    StoryboardSegue
    -0.39
     parfaite
    -0.38
     Trä
    -0.38
     Garantie
    -0.38
    POSITIVE LOGITS
    ,''
    0.89
    .''
    0.88
     ''
    0.86
    ''
    0.85
    ''.
    0.84
    ?''
    0.82
     ``
    0.75
     '''
    0.75
    (''
    0.75
    '',
    0.72
    Act Density 0.166%

    No Known Activations