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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing strong emotions or intense situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    atten
    -0.68
    uma
    -0.67
    ibble
    -0.67
    SPA
    -0.66
    DX
    -0.65
    HER
    -0.63
    itans
    -0.62
    ummer
    -0.60
    nea
    -0.59
    asse
    -0.58
    POSITIVE LOGITS
     thereby
    1.01
     hence
    0.99
     thus
    0.98
     consequently
    0.89
     thence
    0.88
     furthermore
    0.86
     thereafter
    0.85
     therefore
    0.84
     vice
    0.83
     secondly
    0.81
    Act Density 0.186%

    No Known Activations