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

    Neuronpedia

    INDEX
    Explanations

    phrases related to forgetting or dismissing something

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases indicating the concept of "all" or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kamp
    -0.74
    aminer
    -0.69
    ufact
    -0.66
     Peninsula
    -0.62
    yip
    -0.62
    hap
    -0.62
    SHIP
    -0.62
    nom
    -0.60
    oute
    -0.60
    grad
    -0.60
    POSITIVE LOGITS
    ocating
    1.13
     kinds
    1.10
     sorts
    1.08
    igator
    1.06
    udes
    1.03
    igators
    1.02
    usions
    1.01
    uding
    0.95
    ude
    0.91
    usion
    0.88
    Act Density 0.136%

    No Known Activations