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

    Neuronpedia

    INDEX
    Explanations

    instances of conjunctions and punctuation that suggest addition or enumeration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izzato
    -0.17
    ovÃŃ
    -0.16
    odash
    -0.15
    nik
    -0.15
    ÌĨ
    -0.14
    ÑģÑĤÑĥп
    -0.14
    Ay
    -0.14
    ume
    -0.14
    gram
    -0.13
    phia
    -0.13
    POSITIVE LOGITS
     Maz
    0.16
    orious
    0.16
    ernaut
    0.14
     Mapping
    0.14
    uplic
    0.13
    ãģ¯ãģĦ
    0.13
     Ferd
    0.13
     Exp
    0.13
    ruz
    0.13
    zych
    0.13
    Act Density 0.096%

    No Known Activations