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

    Neuronpedia

    INDEX
    Explanations

    assertions and facts related to claims or hypotheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FormBorderStyle
    -0.54
    لاثة
    -0.50
    Décès
    -0.48
    יצוני
    -0.46
     dafür
    -0.44
    Responder
    -0.44
     full
    -0.44
     περιο
    -0.44
    комплек
    -0.44
    mės
    -0.44
    POSITIVE LOGITS
     facts
    1.12
     assertions
    1.11
     statements
    1.09
     statement
    1.06
     Statements
    0.98
     assertion
    0.98
     claim
    0.96
     Assertion
    0.93
    facts
    0.93
    Statements
    0.91
    Act Density 0.734%

    No Known Activations