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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases and references to exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.80
    .*")]
    -0.74
     فريبيس
    -0.67
    ArrowToggle
    -0.66
     consolation
    -0.64
     wireType
    -0.63
    DebuggerNonUser
    -0.63
    ]")]
    -0.63
     Савезне
    -0.63
    RegressionTest
    -0.61
    POSITIVE LOGITS
     just
    0.57
     farlo
    0.55
     except
    0.54
    setVerticalGroup
    0.54
     simply
    0.53
     those
    0.52
     účast
    0.52
    just
    0.51
     unless
    0.50
     fondament
    0.49
    Act Density 0.179%

    No Known Activations