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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expectations and claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.87
    asymp
    -0.86
    ViewFeatures
    -0.84
    httphttps
    -0.72
    chartInstance
    -0.69
     ApiException
    -0.69
     Schrö
    -0.68
    apimachinery
    -0.68
     GenerationType
    -0.64
     Tr
    -0.64
    POSITIVE LOGITS
     Needed
    1.60
     needed
    1.53
    Needed
    1.44
    needed
    1.38
     NEEDED
    1.37
     required
    1.14
     Required
    1.11
     wanted
    1.03
     WANTED
    1.02
     REQUIRED
    1.01
    Act Density 0.165%

    No Known Activations