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

    Neuronpedia

    INDEX
    Explanations

    instances of critical and reflective thinking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     législ
    -0.50
     espoir
    -0.50
     ögon
    -0.49
    Последние
    -0.48
    دارد
    -0.48
    uskas
    -0.47
    tre
    -0.47
    pulumi
    -0.47
     iprot
    -0.47
     medzi
    -0.47
    POSITIVE LOGITS
     aloud
    0.87
     twice
    0.84
     critically
    0.81
     deeply
    0.80
     logically
    0.80
     differently
    0.80
     about
    0.78
     carefully
    0.74
     rationally
    0.73
     fondly
    0.70
    Act Density 0.104%

    No Known Activations