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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Giov
    -0.18
    ingly
    -0.14
     Ear
    -0.14
    çĥ
    -0.14
    -ing
    -0.14
    é§
    -0.14
    bole
    -0.14
    odash
    -0.13
    orate
    -0.13
    ogram
    -0.13
    POSITIVE LOGITS
    olla
    0.15
     Amateur
    0.15
     Rubin
    0.14
    841
    0.14
    ãĥ«ãĤ¯
    0.14
    olin
    0.14
    #__
    0.14
    osemite
    0.14
     tid
    0.14
    ello
    0.14
    Act Density 0.011%

    No Known Activations