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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases and transition words indicating sequencing or context in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CloseOperation
    -1.08
    NUMX
    -1.02
    principalColumn
    -0.98
    MemoryWarning
    -0.93
    Referanser
    -0.93
    Tembelea
    -0.83
    IntoConstraints
    -0.83
    ^(@)
    -0.82
    ########.
    -0.82
     nakalista
    -0.81
    POSITIVE LOGITS
    ↵↵
    0.83
    ↵
    0.65
     The
    0.61
    The
    0.60
    In
    0.55
    (
    0.55
    ↵↵↵
    0.52
    For
    0.51
    I
    0.51
    .
    0.50
    Act Density 1.053%

    No Known Activations