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

    Neuronpedia

    INDEX
    Explanations

    occurrences of possessive form and ownership in the text

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

    .` followed by `s`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suspensão
    -0.49
     called
    -0.47
     vinto
    -0.47
     ask
    -0.47
     ligiloj
    -0.46
     asked
    -0.45
     gius
    -0.45
     chiesto
    -0.45
     day
    -0.44
     call
    -0.44
    POSITIVE LOGITS
    .`
    0.73
    .?
    0.70
    .**
    0.68
    .«
    0.65
    .***
    0.65
    .&
    0.64
    .|
    0.63
    .³
    0.63
    .';
    0.63
    .}
    0.61
    Act Density 0.021%

    No Known Activations