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

    Neuronpedia

    INDEX
    Explanations

    phrases related to stating claims or results in a formal context

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

    presenting information or results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    errHandler
    -0.67
     otomatig
    -0.65
    évaluateur
    -0.65
     GenerationType
    -0.63
    ✨:
    -0.62
    GraphicsUnit
    -0.59
     Normdatei
    -0.57
     ffilmiau
    -0.55
    cillors
    -0.54
    ImageField
    -0.54
    POSITIVE LOGITS
     stated
    0.88
     statement
    0.77
     stating
    0.73
     énon
    0.72
     Statement
    0.72
    stated
    0.70
    Statement
    0.66
     statements
    0.63
    statement
    0.63
     state
    0.62
    Act Density 0.095%

    No Known Activations