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

    Neuronpedia

    INDEX
    Explanations

    instances of quotation marks or dialogue punctuation in the text

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

    ‘ or " followed by possessive 's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.63
    AnimationsModule
    -0.57
     Ferry
    -0.55
    bufio
    -0.53
    +#+#
    -0.50
    Ferry
    -0.50
     initComponents
    -0.49
     Sully
    -0.49
    setOutput
    -0.49
    ferry
    -0.48
    POSITIVE LOGITS
    ‘
    0.65
     plegable
    0.52
     venezolano
    0.46
     libremente
    0.45
     camicia
    0.45
     cubierto
    0.45
     quirúrg
    0.45
     geométrico
    0.44
     costumbre
    0.44
     compartido
    0.42
    Act Density 0.036%

    No Known Activations