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

    Neuronpedia

    INDEX
    Explanations

    words indicating inclusion or additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.76
     beſt
    -0.73
     Anſ
    -0.71
    Семья
    -0.68
     Monfieur
    -0.68
     leaſt
    -0.67
    fauteuil
    -0.67
     firſt
    -0.66
    Köszönöm
    -0.65
    SEGUIR
    -0.65
    POSITIVE LOGITS
     also
    0.88
     همچنین
    0.76
    また
    0.67
     también
    0.63
     Also
    0.63
     También
    0.62
    Also
    0.62
     importantly
    0.62
     other
    0.61
    also
    0.61
    Act Density 0.296%

    No Known Activations