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

    Neuronpedia

    INDEX
    Explanations

    negations and the concept of absence in statements

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

    Followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    wants, needs, or owes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    be
    -1.03
     soient
    -1.03
    Be
    -1.02
     be
    -1.02
     Be
    -0.99
     siano
    -0.84
    BE
    -0.77
     sejam
    -0.77
     BE
    -0.70
     aient
    -0.66
    POSITIVE LOGITS
     deserve
    1.08
     belong
    1.07
    LookAnd
    1.03
     need
    0.97
     seem
    0.95
     owe
    0.93
     know
    0.92
    #+#
    0.87
     want
    0.86
     require
    0.83
    Act Density 0.189%

    No Known Activations