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

    Neuronpedia

    INDEX
    Explanations

    subjective statements about personal beliefs and experiences

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

    Followed by the verb "to be"

    np_acts-logits-general · gemini-2.0-flash

    forms of "to be"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.73
     Did
    -0.65
    Did
    -0.64
    did
    -0.64
     did
    -0.61
    lasty
    -0.55
    aughey
    -0.54
    Does
    -0.52
    does
    -0.51
    styleable
    -0.50
    POSITIVE LOGITS
     is
    1.38
     are
    1.05
     là
    0.94
     είναι
    0.90
    是
    0.86
     être
    0.85
     essere
    0.83
     be
    0.79
     бути
    0.78
     být
    0.77
    Act Density 0.365%

    No Known Activations