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

    Neuronpedia

    INDEX
    Explanations

    references to behavior and behavioral changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    risten
    -0.69
     Milne
    -0.68
     Laurens
    -0.68
     Clooney
    -0.66
     gzip
    -0.62
     Koning
    -0.62
     Clarkson
    -0.61
     deadline
    -0.61
    tigma
    -0.61
    amak
    -0.61
    POSITIVE LOGITS
     behavior
    2.89
     Behavior
    2.68
     behaviour
    2.67
    behavior
    2.55
     behaviors
    2.51
     BEHAVIOR
    2.49
    Behavior
    2.39
     Behaviour
    2.38
    behaviour
    2.31
     behaviours
    2.30
    Act Density 0.091%

    No Known Activations