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

    Neuronpedia

    INDEX
    Explanations

    positive actions or uplifting events

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "shift" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cin
    -0.70
     PV
    -0.64
     QC
    -0.62
     vul
    -0.61
     bat
    -0.61
     bacter
    -0.60
     Bam
    -0.60
     Cardinals
    -0.59
     polic
    -0.59
     Byr
    -0.58
    POSITIVE LOGITS
    ifts
    3.95
    ifting
    3.69
    ifted
    3.30
    ifter
    2.82
    ift
    2.76
    IFT
    2.44
    ifty
    1.20
    lift
    1.18
     Lift
    1.05
    immer
    1.03
    Act Density 0.014%

    No Known Activations