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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating increases or reductions in quantity or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.65
     تانيه
    -0.62
     gyhoeddwyd
    -0.62
     ottima
    -0.61
     máis
    -0.61
     buone
    -0.61
     incroy
    -0.60
     réfugi
    -0.60
     suffisamment
    -0.60
     más
    -0.60
    POSITIVE LOGITS
     likely
    0.81
     like
    0.63
     pronounced
    0.59
     frequently
    0.57
     complete
    0.56
     consistent
    0.55
     often
    0.55
     readily
    0.54
     frequent
    0.54
     easily
    0.54
    Act Density 0.190%

    No Known Activations