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

    Neuronpedia

    INDEX
    Explanations

    grammatical structures and conjunctions within familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essed
    -0.15
    ew
    -0.15
    ÑĦÑĸ
    -0.14
    eview
    -0.13
    ique
    -0.13
    PLAIN
    -0.13
    ÅĽnie
    -0.13
    peats
    -0.13
     Tham
    -0.13
    EEK
    -0.13
    POSITIVE LOGITS
     Manning
    0.14
    OMP
    0.14
    iye
    0.13
    atr
    0.13
     Kop
    0.13
    arrass
    0.13
    ظÙĩ
    0.13
    @nate
    0.13
    USTER
    0.12
     Kauf
    0.12
    Act Density 0.008%

    No Known Activations