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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or indecision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odal
    -0.19
    udas
    -0.16
    inspace
    -0.14
    çĶĺ
    -0.14
    enis
    -0.14
    POCH
    -0.14
    ANGLES
    -0.14
    otts
    -0.14
     lever
    -0.13
    anean
    -0.13
    POSITIVE LOGITS
     else
    0.18
     Else
    0.17
    Else
    0.16
    idget
    0.15
     Tooth
    0.15
     Cottage
    0.15
     ELSE
    0.15
    atore
    0.14
    iÄħ
    0.14
    iri
    0.14
    Act Density 0.068%

    No Known Activations