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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the verb "haber" and its conjugations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gregar
    -0.19
    piar
    -0.17
    imen
    -0.17
    itize
    -0.17
    dar
    -0.16
    regar
    -0.15
    errar
    -0.15
    egie
    -0.15
    ominator
    -0.15
    voy
    -0.14
    POSITIVE LOGITS
     sido
    0.26
     hecho
    0.23
     dado
    0.22
     estado
    0.20
     corrid
    0.20
     puesto
    0.19
     visto
    0.19
     partido
    0.18
     realizado
    0.18
     pod
    0.18
    Act Density 0.028%

    No Known Activations