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

    Neuronpedia

    INDEX
    Explanations

    references to objects or concepts related to rings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ring."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.77
    icago
    -0.75
    essors
    -0.72
    irrel
    -0.70
    UGE
    -0.69
    éĹĺ
    -0.68
    tical
    -0.68
     Fiorina
    -0.67
     autop
    -0.66
     Fraz
    -0.65
    POSITIVE LOGITS
    tone
    1.38
    tones
    1.24
    leader
    1.22
    leaders
    1.18
    worm
    1.08
    rings
    1.02
    git
    1.01
    wra
    0.99
    mail
    0.91
    Ring
    0.84
    Act Density 0.014%

    No Known Activations