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

    Neuronpedia

    INDEX
    Explanations

    instances of playful or humorous interactions and moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.55
     arise
    -0.53
     involve
    -0.53
    volves
    -0.52
    EClass
    -0.50
     occur
    -0.49
    +:+
    -0.49
    tedly
    -0.48
    حات
    -0.47
    onnay
    -0.46
    POSITIVE LOGITS
     took
    1.71
     went
    1.62
     got
    1.59
     walked
    1.54
     gave
    1.51
     wrote
    1.50
     drove
    1.49
     tried
    1.48
     waited
    1.45
     drank
    1.44
    Act Density 0.780%

    No Known Activations