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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal responsibility and guilt

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

    blame, fault, guilt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     embaraz
    -0.43
     cerrada
    -0.42
     aikaa
    -0.42
     libremente
    -0.41
    itemBuilder
    -0.40
    embols
    -0.40
     rhestr
    -0.40
     LIRE
    -0.40
     Mø
    -0.40
     Caballero
    -0.40
    POSITIVE LOGITS
     Blame
    1.02
     blame
    0.96
    Blame
    0.96
    blame
    0.88
    fault
    0.83
     Fault
    0.83
     fault
    0.82
    Fault
    0.77
     Guilt
    0.76
    FAULT
    0.75
    Act Density 0.030%

    No Known Activations