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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistical procedures and assumptions in scientific studies

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

    people, everyone, employees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.94
    <unused43>
    -0.89
    <unused8>
    -0.89
    <unused28>
    -0.88
    <unused41>
    -0.88
    <unused16>
    -0.88
    <unused52>
    -0.88
    <unused74>
    -0.88
    <unused68>
    -0.88
    <pad>
    -0.88
    POSITIVE LOGITS
     everyone
    0.59
     someone
    0.58
     they
    0.56
     each
    0.49
     people
    0.48
     somebody
    0.44
     employees
    0.43
     Each
    0.43
     children
    0.43
     SOMEONE
    0.43
    Act Density 0.398%

    No Known Activations