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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <=",
    -0.78
    TestingModule
    -0.68
     ddelweddau
    -0.64
     referrerpolicy
    -0.62
    IntoConstraints
    -0.59
    ModelForm
    -0.59
     Numerade
    -0.59
     ModelExpression
    -0.58
    enderror
    -0.57
    +#+#
    -0.56
    POSITIVE LOGITS
     decir
    0.88
    prnewswire
    0.77
     say
    0.72
     seja
    0.68
     heißt
    0.66
     cioè
    0.65
     znaczy
    0.62
     means
    0.59
    say
    0.57
     mean
    0.56
    Act Density 0.141%

    No Known Activations