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

    Neuronpedia

    INDEX
    Explanations

    strong affirmations or intensifiers expressing certainty and agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Henson
    -0.71
     Guen
    -0.69
    in
    -0.64
     patro
    -0.63
     einges
    -0.63
     Henne
    -0.62
     Nestor
    -0.62
    icker
    -0.61
    Vea
    -0.61
    an
    -0.61
    POSITIVE LOGITS
     absolutely
    1.38
    absolutely
    1.32
     Absolutely
    1.31
    UTELY
    1.29
    Absolutely
    1.22
    olutamente
    1.19
     absolument
    1.10
     absolutamente
    1.03
     assolutamente
    0.94
     ABSOL
    0.93
    Act Density 0.064%

    No Known Activations