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

    Neuronpedia

    INDEX
    Explanations

    mentions of the city "Tempe"

    oai_token-act-pair · gpt-3.5-turbo

    the term "pe" and its variations related to food or cultural subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     weekday
    -0.67
     responsibility
    -0.64
     overload
    -0.63
     forwarding
    -0.59
     casualties
    -0.59
     odds
    -0.59
     outsourcing
    -0.58
     ALS
    -0.58
     Err
    -0.57
     negligence
    -0.56
    POSITIVE LOGITS
    pe
    4.33
    pes
    2.33
    Pe
    1.83
    pec
    1.51
    PE
    1.49
    pell
    1.47
    peg
    1.43
    peer
    1.40
    pee
    1.38
    peak
    1.27
    Act Density 0.008%

    No Known Activations