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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain textual structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akis
    -0.16
    iele
    -0.15
    hap
    -0.15
    .scalablytyped
    -0.14
     orth
    -0.14
    _ABI
    -0.14
    achuset
    -0.14
    SWG
    -0.14
    bsp
    -0.14
    orth
    -0.14
    POSITIVE LOGITS
    zÄĻ
    0.16
     pred
    0.15
    ollo
    0.14
    uggy
    0.14
    å®
    0.14
    -font
    0.14
    rie
    0.14
    ott
    0.14
     mol
    0.13
     rosa
    0.13
    Act Density 0.018%

    No Known Activations