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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest emotional or psychological states and their implications

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

    Forms of the verb "to be"

    np_acts-logits-general · gemini-2.0-flash

    state of being or quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     its
    -1.50
     itself
    -1.42
    Its
    -1.36
     Its
    -1.34
    itself
    -1.20
    它的
    -1.15
     Itself
    -1.07
    它
    -1.02
     яке
    -0.99
    its
    -0.97
    POSITIVE LOGITS
     themselves
    1.67
    themselves
    1.41
     are
    1.29
     were
    1.23
     serem
    1.23
     ones
    1.03
     aren
    0.96
    are
    0.92
    were
    0.92
     weren
    0.90
    Act Density 2.353%

    No Known Activations