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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement or disagreement in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uai
    -0.15
    ounter
    -0.15
    åde
    -0.15
    rol
    -0.14
    uil
    -0.14
    rop
    -0.14
    apa
    -0.14
    ogui
    -0.14
    umer
    -0.13
    illet
    -0.13
    POSITIVE LOGITS
     completely
    0.27
     entirely
    0.26
     totally
    0.25
     sentiments
    0.23
     except
    0.21
     sentiment
    0.21
     assessment
    0.21
     partially
    0.21
     partly
    0.19
     Totally
    0.19
    Act Density 0.113%

    No Known Activations