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

    Neuronpedia

    INDEX
    Explanations

    the presence of the verb "is" in various contexts

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

    is followed by state or condition check

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſche
    -0.67
     deleteUser
    -0.56
     ſtate
    -0.53
     ſol
    -0.53
    Vag
    -0.53
    pthread
    -0.53
     pleaſure
    -0.53
    trand
    -0.52
    Pug
    -0.52
    Vain
    -0.52
    POSITIVE LOGITS
     is
    1.39
    is
    1.03
     Is
    1.02
    Is
    0.98
     are
    0.93
     IS
    0.76
     está
    0.75
     was
    0.74
     nakalista
    0.72
     είναι
    0.71
    Act Density 0.572%

    No Known Activations