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

    Neuronpedia

    INDEX
    Explanations

    words and terms associated with specific technical details or mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     compañ
    -0.53
    parsedMessage
    -0.50
     Geduld
    -0.48
     Senado
    -0.48
     civilización
    -0.47
     Inscrivez
    -0.47
     herencia
    -0.46
     Comunicación
    -0.46
     emple
    -0.44
    untung
    -0.43
    POSITIVE LOGITS
     squ
    0.61
     ret
    0.59
     cap
    0.59
    addPreferredGap
    0.58
     pret
    0.57
     vPvB
    0.56
     flu
    0.56
     fl
    0.55
     fire
    0.54
     sp
    0.54
    Act Density 0.741%

    No Known Activations