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

    Neuronpedia

    INDEX
    Explanations

    words related to heightened states or excessiveness

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "hyper" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ello
    -0.82
     Continued
    -0.74
    INGS
    -0.72
     Settlement
    -0.72
     Peoples
    -0.70
    ivity
    -0.70
    oured
    -0.69
    irements
    -0.69
    UE
    -0.69
    eca
    -0.69
    POSITIVE LOGITS
     hyper
    1.30
     hyp
    1.12
    bole
    1.11
    hyper
    1.09
    visor
    1.07
    bol
    1.00
    hyp
    0.92
    dimension
    0.88
     aggro
    0.83
     mascul
    0.82
    Act Density 0.009%

    No Known Activations