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

    Neuronpedia

    INDEX
    Explanations

    words related to expressions of strong emotions or support

    oai_token-act-pair · gpt-3.5-turbo

    mentions of outpourings of support and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Labrador
    -0.87
    dar
    -0.78
     Crown
    -0.73
     Galile
    -0.69
     Roh
    -0.66
     lodge
    -0.65
     Sul
    -0.65
     cave
    -0.64
     Rath
    -0.63
     Hab
    -0.62
    POSITIVE LOGITS
     outp
    1.33
    imates
    0.96
    issance
    0.94
     ILCS
    0.88
    acers
    0.83
    soType
    0.82
    efully
    0.80
    ributes
    0.78
    oresc
    0.77
    orescence
    0.77
    Act Density 0.013%

    No Known Activations