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

    Neuronpedia

    INDEX
    Explanations

    specific entities and actions within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.87
    antaranya
    -0.69
    OGND
    -0.64
    ⓧ
    -0.64
    +#+#
    -0.59
    jenigen
    -0.54
    zelfde
    -0.52
    TryDecodeAsNil
    -0.50
    ņas
    -0.50
     dieselben
    -0.50
    POSITIVE LOGITS
    ……"
    0.59
    ···
    0.48
    …]
    0.47
     …)
    0.46
    ...";
    0.46
    <eos>
    0.45
    …,
    0.44
     ...)
    0.44
    ..]
    0.44
    ...).
    0.43
    Act Density 1.497%

    No Known Activations