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

    Neuronpedia

    INDEX
    Explanations

    keywords related to setting tasks and taking action

    oai_token-act-pair · gpt-3.5-turbo

    statements related to urgency or critical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stuff
    -0.85
     nicer
    -0.79
     Yeah
    -0.79
     dudes
    -0.77
     yeah
    -0.76
    Yeah
    -0.76
     dude
    -0.74
     guy
    -0.74
     crap
    -0.70
     weird
    -0.69
    POSITIVE LOGITS
     [/
    0.95
    osate
    0.91
    [/
    0.80
    îĢ
    0.79
    Reviewer
    0.75
     herein
    0.75
    ratom
    0.72
    tis
    0.72
     Inquiry
    0.70
    ankind
    0.70
    Act Density 1.108%

    No Known Activations