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

    Neuronpedia

    INDEX
    Explanations

    expressions of confusion or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ughs
    -0.17
    .scalablytyped
    -0.17
    itud
    -0.15
    reo
    -0.15
    _configure
    -0.15
     LPARAM
    -0.15
    irst
    -0.14
    leans
    -0.14
    éo
    -0.14
    ãĥ³ãĤ¹
    -0.14
    POSITIVE LOGITS
    /conf
    0.27
    ingly
    0.20
     about
    0.19
    ÌĪ
    0.17
     confusion
    0.16
    etti
    0.16
    -cut
    0.16
    ĶĶ
    0.15
    ly
    0.15
    about
    0.15
    Act Density 0.024%

    No Known Activations