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

    Neuronpedia

    INDEX
    Explanations

    the word "persistent."

    oai_token-act-pair · gpt-4-turbo

    words related to persistence or long-lasting effects

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to persistence and ongoing effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.89
    hens
    -0.80
    ranch
    -0.80
    abad
    -0.77
    SB
    -0.74
    enes
    -0.73
    hops
    -0.73
    yer
    -0.72
    swick
    -0.72
    erala
    -0.71
    POSITIVE LOGITS
     persistence
    1.02
     persistent
    0.95
     persist
    0.88
    uously
    0.84
    ently
    0.79
     veget
    0.77
     veter
    0.76
     viol
    0.76
     strugg
    0.74
     offender
    0.73
    Act Density 0.010%

    No Known Activations