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

    Neuronpedia

    INDEX
    Explanations

    personal perspectives or opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "I," indicating personal reflections or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TBD
    -0.69
     totality
    -0.64
     optics
    -0.64
     unspecified
    -0.63
     Deadline
    -0.62
    INGTON
    -0.58
     Resurrection
    -0.57
    URR
    -0.57
    bones
    -0.57
     Replacement
    -0.57
    POSITIVE LOGITS
    've
    1.16
    'm
    1.15
     prefer
    1.04
    deals
    1.03
     myself
    1.00
    ronic
    0.99
     rarely
    0.97
     often
    0.94
     am
    0.93
     cringe
    0.93
    Act Density 0.289%

    No Known Activations