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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scientific concepts and phenomena

    oai_token-act-pair · gpt-3.5-turbo

    references to living organisms and their corresponding systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Veter
    -0.74
     Shame
    -0.72
     Crusade
    -0.71
    panic
    -0.66
     THANK
    -0.65
     Savings
    -0.63
     Ladies
    -0.63
    ovember
    -0.62
     Abuse
    -0.62
    grim
    -0.61
    POSITIVE LOGITS
     encoded
    1.17
     embod
    1.12
    omorphic
    1.01
     interacting
    1.00
     governed
    0.97
     describ
    0.95
     analogous
    0.94
     constructed
    0.94
     inscribed
    0.93
     composed
    0.93
    Act Density 0.470%

    No Known Activations