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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty and assessment of value or quality in a context

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

    Signals concessive clauses

    np_acts-logits-general · gemini-2.0-flash

    but however

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ri
    -0.36
    (){
    -0.35
     «
    -0.35
     
    -0.35
     (
    -0.35
    ()">
    -0.34
    ()
    -0.34
    ()"
    -0.34
    rios
    -0.33
    turas
    -0.33
    POSITIVE LOGITS
     however
    2.76
    however
    2.56
     entanto
    2.50
     però
    2.36
    However
    2.10
     όμως
    2.09
     însă
    2.06
     cependant
    2.06
     toutefois
    2.02
     though
    2.02
    Act Density 0.555%

    No Known Activations