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

    Neuronpedia

    INDEX
    Explanations

    words related to revisiting, reappearance, or resurfacing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reevaluation or reconsideration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the prefix "reapp-"

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Negative Logits
     Parenthood
    -0.72
    Fi
    -0.71
    thouse
    -0.69
     Gujar
    -0.67
    ahi
    -0.67
    chain
    -0.67
    Irish
    -0.67
    Person
    -0.67
    WARE
    -0.65
    Indiana
    -0.65
    POSITIVE LOGITS
     recapt
    1.05
     tremend
    0.88
     recons
    0.87
     reload
    0.87
     recon
    0.86
     recol
    0.85
     reapp
    0.82
     reintrodu
    0.81
    accompan
    0.81
     recollection
    0.80
    Act Density 0.020%

    No Known Activations