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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a need for action or investigation

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

    Following the word "to"

    np_acts-logits-general · gemini-2.0-flash

    invitation to take

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    -0.40
     have
    -0.38
     tanong
    -0.36
     versions
    -0.30
    一
    -0.29
     I
    -0.29
     Have
    -0.29
    ea
    -0.29
     it
    -0.28
     if
    -0.28
    POSITIVE LOGITS
    Билгалдахарш
    0.75
    parsedMessage
    0.68
     CURIAM
    0.64
    <unused43>
    0.64
    [@BOS@]
    0.63
    <unused68>
    0.63
    <unused42>
    0.63
    <pad>
    0.63
     deſſen
    0.63
    <unused3>
    0.63
    Act Density 1.135%

    No Known Activations