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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    basicConfig
    -0.67
    -0.56
    HasForeignKey
    -0.52
    ::_('
    -0.52
    ::~
    -0.52
    ης
    -0.49
    گانی
    -0.49
    MessageTagHelper
    -0.48
    他想
    -0.46
    gdx
    -0.46
    POSITIVE LOGITS
     trust
    1.91
    trust
    1.66
     Trust
    1.58
    Trust
    1.54
     believe
    1.53
     TRUST
    1.46
    believe
    1.45
     Believe
    1.39
    Believe
    1.37
    TRUST
    1.31
    Act Density 0.218%

    No Known Activations