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

    Neuronpedia

    INDEX
    Explanations

    conditional statements

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

    if you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.59
     ilustracja
    -0.55
     promocional
    -0.54
     illustrationer
    -0.54
    ſelves
    -0.52
     ब्रेकडाउन
    -0.52
     ſever
    -0.52
     tuyo
    -0.50
    NewLabel
    -0.50
     Wiktionnaire
    -0.50
    POSITIVE LOGITS
     I
    0.45
    Anyone
    0.40
    I
    0.39
     Anyone
    0.38
     anyone
    0.38
    Wanna
    0.37
    oredCriteria
    0.37
     Had
    0.37
    Didn
    0.35
     you
    0.35
    Act Density 0.041%

    No Known Activations