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

    Neuronpedia

    INDEX
    Explanations

    verbs related to causing harm or negative impact

    oai_token-act-pair · gpt-3.5-turbo

    terms related to being spared or harmed in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Evolution
    -0.64
     stale
    -0.64
     Rowe
    -0.63
     aggregate
    -0.63
     explo
    -0.61
     Analytics
    -0.60
     Register
    -0.59
    LECT
    -0.59
    Sing
    -0.59
    Fill
    -0.58
    POSITIVE LOGITS
     spared
    3.83
     sparing
    1.81
     spare
    1.38
     unaffected
    1.01
     pard
    0.98
     harmed
    0.87
    orah
    0.87
     Winchester
    0.85
     shielded
    0.81
    hyde
    0.77
    Act Density 0.033%

    No Known Activations