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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rewards and incentives within a payment structure

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

    Preceding "by" (often related to payment or calculation)

    np_acts-logits-general · gemini-2.0-flash

    by paying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fijo
    -0.36
     confiable
    -0.35
     snippetHide
    -0.33
     inclusión
    -0.33
     universidad
    -0.32
     amado
    -0.32
     posibil
    -0.32
     autoridad
    -0.31
     mulig
    -0.31
     möj
    -0.30
    POSITIVE LOGITS
     nakalista
    0.74
    /**
    0.63
    oredCriteria
    0.58
     successfully
    0.58
    Aholisi
    0.56
    Sklici
    0.56
    ImageContext
    0.54
    Әдәбият
    0.54
    Filmo
    0.54
     successful
    0.53
    Act Density 0.294%

    No Known Activations