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

    Neuronpedia

    INDEX
    Explanations

    words related to locations or travel destinations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or entity named "Cadad" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     backwards
    -0.66
     pity
    -0.63
     pole
    -0.62
     Manit
    -0.62
     Sunshine
    -0.61
     corrective
    -0.60
     trout
    -0.59
     poles
    -0.59
    ideshow
    -0.59
     stret
    -0.58
    POSITIVE LOGITS
    visor
    1.23
    venture
    1.20
    ventures
    1.13
    vised
    1.09
    vance
    1.06
    aily
    1.06
    visors
    1.05
    illac
    1.03
    rome
    1.02
    rill
    1.01
    Act Density 0.040%

    No Known Activations