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

    Neuronpedia

    INDEX
    Explanations

    sentence starters and transitional phrases that indicate a change in thought or a continuation of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    %";
    -0.93
    %]
    -0.88
    NUMX
    -0.87
    HasForeignKey
    -0.85
    ^(@)
    -0.85
    brainly
    -0.85
    CloseOperation
    -0.85
    MemoryWarning
    -0.85
     MainAxisSize
    -0.84
    ousands
    -0.84
    POSITIVE LOGITS
    ↵↵
    1.10
    ↵↵↵
    0.69
    .
    0.68
    The
    0.64
    <eos>
    0.62
    UnusedPrivate
    0.61
    ↵
    0.60
     The
    0.60
     Réponses
    0.58
    ↵↵↵↵↵
    0.57
    Act Density 0.621%

    No Known Activations