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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing strong descriptors, particularly the word "very."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orre
    -0.17
    ÑģÑĤÑİ
    -0.15
    оÑĢÑıд
    -0.15
    owed
    -0.14
    oris
    -0.14
    prot
    -0.14
    ory
    -0.13
    ustr
    -0.13
    utch
    -0.13
    ály
    -0.13
    POSITIVE LOGITS
     same
    0.24
    same
    0.19
     essence
    0.18
     SAME
    0.18
     thing
    0.18
     opposite
    0.16
     mention
    0.15
     existence
    0.15
     worst
    0.15
    790
    0.15
    Act Density 0.019%

    No Known Activations