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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating likelihood or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovan
    -0.15
    aca
    -0.15
     herself
    -0.15
     its
    -0.14
    ôi
    -0.14
    jp
    -0.14
    pson
    -0.14
    stin
    -0.14
    enburg
    -0.13
    ediator
    -0.13
    POSITIVE LOGITS
    agar
    0.14
    Pitch
    0.14
     поÑĢÑıд
    0.13
    ël
    0.13
    ç²Ĺ
    0.13
     largo
    0.13
    iche
    0.13
    eree
    0.13
    rnek
    0.13
    /***/
    0.13
    Act Density 0.055%

    No Known Activations