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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and negations

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

    "Or not" after a question

    np_acts-logits-general · gemini-2.0-flash

    whether or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.72
    ChildScrollView
    -0.63
    CloseOperation
    -0.61
    StoryboardSegue
    -0.60
    __(/*!
    -0.58
     doubtnut
    -0.58
     verhind
    -0.56
     Pape
    -0.55
    rouvez
    -0.55
     Grosso
    -0.54
    POSITIVE LOGITS
     whether
    0.81
     not
    0.76
     something
    0.69
    whether
    0.62
    それとも
    0.62
     تانيه
    0.60
     it
    0.59
     خیر
    0.58
     otherwise
    0.58
     just
    0.57
    Act Density 0.115%

    No Known Activations