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

    Neuronpedia

    INDEX
    Explanations

    corrected values and their relationships to interventions and adjustments in data analysis

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

    Text preceding a correction, model, or adjustment

    np_acts-logits-general · gemini-2.0-flash

    corrected visual acuity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.85
     للمعارف
    -0.85
    <unused79>
    -0.83
    <unused14>
    -0.83
    <unused41>
    -0.83
    <unused23>
    -0.83
    <unused43>
    -0.83
    <unused8>
    -0.83
    [@BOS@]
    -0.83
    <unused3>
    -0.83
    POSITIVE LOGITS
    ↵↵
    0.24
     makes
    0.24
     P
    0.24
     h
    0.23
    hti
    0.23
     womit
    0.22
     tun
    0.22
    4
    0.22
     making
    0.22
     ح
    0.22
    Act Density 1.079%

    No Known Activations