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

    Neuronpedia

    INDEX
    Explanations

    concepts related to healthcare and medical procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to consciousness and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tanz
    -0.56
     Ded
    -0.51
     haw
    -0.51
     advoc
    -0.49
     peac
    -0.48
     bluff
    -0.48
     Siber
    -0.48
    olic
    -0.48
    Balt
    -0.48
     IPS
    -0.47
    POSITIVE LOGITS
     violates
    0.87
     illustrates
    0.85
     constitutes
    0.83
     seemed
    0.83
     seems
    0.83
     amounted
    0.81
     suggests
    0.81
     resulted
    0.78
    )).
    0.78
     surfaced
    0.77
    Act Density 1.454%

    No Known Activations