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

    Neuronpedia

    INDEX
    Explanations

    the start of new sections or entries in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.71
    ন্দ
    -0.54
    Бахар
    -0.53
    vič
    -0.51
    дель
    -0.50
    BagConstraints
    -0.49
     <<<<<<<<<<<<<<
    -0.47
    uebe
    -0.47
     Strö
    -0.47
    msgTypes
    -0.46
    POSITIVE LOGITS
    httphttps
    0.72
    Portale
    0.65
    hooter
    0.64
     betweenstory
    0.64
    KommentareTeilen
    0.63
    odyear
    0.61
    anyahu
    0.59
    YourGuide
    0.59
    ArgsConstructor
    0.59
    ]));
    0.59
    Act Density 0.210%

    No Known Activations