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

    Neuronpedia

    INDEX
    Explanations

    excessive or overwhelming qualities in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ry
    -0.17
    odb
    -0.15
     Ged
    -0.15
    ize
    -0.15
    cia
    -0.15
     mare
    -0.14
    ãģįãģŁ
    -0.14
    jerne
    -0.14
    iders
    -0.14
    NullOrEmpty
    -0.14
    POSITIVE LOGITS
     TOO
    0.21
     Too
    0.20
    Too
    0.18
    too
    0.18
     too
    0.18
    -too
    0.18
    151
    0.16
    gether
    0.16
    ÃŃst
    0.16
    152
    0.15
    Act Density 0.084%

    No Known Activations