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

    Neuronpedia

    INDEX
    Explanations

    references to collective pronouns or expressions of togetherness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anticipate
    -0.16
    uja
    -0.15
    ANNOT
    -0.15
    ~-
    -0.15
    apan
    -0.15
    ÑĢÑĥб
    -0.15
    оÑİ
    -0.15
    EXPECT
    -0.14
    ulan
    -0.14
    nek
    -0.14
    POSITIVE LOGITS
    'll
    0.17
    'd
    0.16
     typical
    0.15
    512
    0.15
    anz
    0.14
    518
    0.14
    _ctxt
    0.14
     ill
    0.14
    '
    0.14
     cas
    0.13
    Act Density 0.092%

    No Known Activations