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

    Neuronpedia

    INDEX
    Explanations

    statements or suggestions of necessity or importance

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afia
    -0.74
    atures
    -0.71
    terday
    -0.67
    plex
    -0.66
    ossus
    -0.64
    enary
    -0.64
    risis
    -0.63
    riott
    -0.63
    orer
    -0.61
    arta
    -0.59
    POSITIVE LOGITS
     construed
    0.98
     interpreted
    0.96
     judged
    0.94
     able
    0.89
    fall
    0.84
     deemed
    0.84
     considered
    0.83
     viewed
    0.83
     dictated
    0.82
     handled
    0.81
    Act Density 0.212%

    No Known Activations