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

    Neuronpedia

    INDEX
    Explanations

    mentions of favorites or preferred selections in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    H
    -0.55
    ra
    -0.54
    h
    -0.54
    ende
    -0.50
     I
    -0.50
    ResumeLayout
    -0.50
    R
    -0.48
    er
    -0.48
    comp
    -0.48
    ра
    -0.47
    POSITIVE LOGITS
     pastime
    0.98
     <<<<<<<<<<<<<<
    0.87
    ourites
    0.86
     doInBackground
    0.83
     Favorites
    0.81
     Theſe
    0.77
     favorites
    0.75
     IBOutlet
    0.74
    ellido
    0.74
     pleaſure
    0.73
    Act Density 0.061%

    No Known Activations