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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "A" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.47
    exitRule
    -0.44
    RTHOOK
    -0.44
     nakalista
    -0.43
    didSet
    -0.41
    UVWXYZ
    -0.40
    afficheront
    -0.38
    RegressionTest
    -0.38
    Personendaten
    -0.37
    Ӕ
    -0.37
    POSITIVE LOGITS
     betweenstory
    0.59
     Erskine
    0.53
    \{\\
    0.51
    thentication
    0.50
    Commissioner
    0.49
       
    0.49
    tershire
    0.48
     figliu
    0.47
    如下图
    0.47
    assembling
    0.47
    Act Density 0.718%

    No Known Activations