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

    Neuronpedia

    INDEX
    Explanations

    instances of confusion and uncertainty in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ughs
    -0.17
     LPARAM
    -0.15
    寸
    -0.14
    .scalablytyped
    -0.14
    éo
    -0.14
    inals
    -0.14
    aylor
    -0.14
    lid
    -0.14
    itud
    -0.13
    ylko
    -0.13
    POSITIVE LOGITS
    /conf
    0.30
    ingly
    0.22
     about
    0.20
    ÌĪ
    0.19
    etti
    0.18
     confusion
    0.18
    olini
    0.16
    ly
    0.16
     confuse
    0.16
    ĶĶ
    0.15
    Act Density 0.026%

    No Known Activations