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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and connectors that imply relationships or conditions between statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding conjunctions or commas

    np_acts-logits-general · gemini-2.0-flash

    coordinate phrases and clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fraid
    -0.54
    aware
    -0.53
     Wrote
    -0.53
     Aware
    -0.51
    ardless
    -0.49
    ोंने
    -0.49
    Forgot
    -0.48
     preferring
    -0.47
     wishing
    -0.46
    Recuerda
    -0.46
    POSITIVE LOGITS
     contains
    1.06
     is
    1.01
     consists
    0.95
     can
    0.94
     will
    0.88
     may
    0.87
     comprises
    0.87
     involves
    0.87
     includes
    0.87
     nécess
    0.87
    Act Density 0.718%

    No Known Activations