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

    Neuronpedia

    INDEX
    Explanations

    non-specific pronouns and common phrases related to uncertainty and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BagConstraints
    -0.87
     jsPsych
    -0.80
    AddTagHelper
    -0.79
     initComponents
    -0.77
     ComVisible
    -0.75
    Personendaten
    -0.74
    adpleegd
    -0.73
    OrNil
    -0.70
     Meksiku
    -0.69
    BeginContext
    -0.69
    POSITIVE LOGITS
     been
    0.96
     is
    0.92
     be
    0.91
     also
    0.84
     definitely
    0.78
     not
    0.78
     always
    0.74
     are
    0.70
     was
    0.70
     still
    0.69
    Act Density 0.165%

    No Known Activations