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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to locations and people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pesada
    -0.40
     femenina
    -0.36
     masculina
    -0.35
     gustan
    -0.35
     secos
    -0.35
     pública
    -0.35
     mauvaise
    -0.35
     masculinos
    -0.34
     negra
    -0.34
     contigo
    -0.34
    POSITIVE LOGITS
    <unused43>
    0.83
    <unused76>
    0.82
    <unused41>
    0.82
    <unused17>
    0.82
    <unused23>
    0.82
    <pad>
    0.82
    <unused20>
    0.82
    <unused74>
    0.82
    <unused42>
    0.82
    <unused51>
    0.82
    Act Density 0.024%

    No Known Activations