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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    the word "shop" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confir
    -0.80
     numbered
    -0.79
    etheless
    -0.74
     Ajax
    -0.74
     foil
    -0.72
    ãģĨ
    -0.72
     fencing
    -0.71
     prevail
    -0.69
    é¾įå¥ij士
    -0.68
    anwhile
    -0.68
    POSITIVE LOGITS
    allow
    1.11
    ooting
    1.11
    apesh
    1.07
    ifty
    1.07
    uff
    1.06
    ameless
    1.04
    attered
    1.02
    orts
    0.99
    anks
    0.98
    apeshifter
    0.98
    Act Density 0.020%

    No Known Activations