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

    Neuronpedia

    INDEX
    Explanations

    references to communication and dialogue between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ratto
    -0.40
    mapTo
    -0.39
     topic
    -0.38
     ability
    -0.38
     figuring
    -0.38
     slate
    -0.36
    xic
    -0.34
     Patterns
    -0.33
     os
    -0.33
     internal
    -0.33
    POSITIVE LOGITS
     bluntly
    0.71
     explicitly
    0.62
    WaitGroup
    0.61
     plainly
    0.60
     sternly
    0.60
     Савезне
    0.59
     verbally
    0.58
     informally
    0.57
     why
    0.57
     <=",
    0.56
    Act Density 0.198%

    No Known Activations