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

    Neuronpedia

    INDEX
    Explanations

    expressions related to uncertainty or the idea that certain things may not be as they appear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igne
    -0.16
    visor
    -0.15
    è³
    -0.15
     GD
    -0.14
    rze
    -0.14
    ength
    -0.14
    mobx
    -0.14
    ipher
    -0.14
    ýt
    -0.13
    etti
    -0.13
    POSITIVE LOGITS
     certain
    0.15
    SZ
    0.15
    ãİ
    0.14
    cu
    0.14
     cầu
    0.14
     Certain
    0.14
    /Card
    0.14
    .gwt
    0.14
    Certain
    0.14
    Ign
    0.13
    Act Density 0.098%

    No Known Activations