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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing repetition or recurrence

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing repetition or recurring events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theft
    -0.67
    gs
    -0.60
     Trouble
    -0.59
    Thirty
    -0.59
    Writ
    -0.59
    assis
    -0.57
    Prot
    -0.56
     Serious
    -0.55
    iquette
    -0.55
    ories
    -0.55
    POSITIVE LOGITS
    etheless
    1.00
     again
    0.82
    theless
    0.75
    igree
    0.73
     until
    0.72
    )=(
    0.72
     repeated
    0.69
    again
    0.67
     AGA
    0.66
     glued
    0.65
    Act Density 0.034%

    No Known Activations