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

    Neuronpedia

    INDEX
    Explanations

    terms related to diagnostic processes and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anſ
    -0.53
     purpoſe
    -0.53
    MigrationBuilder
    -0.53
     pleaſure
    -0.52
     minuter
    -0.50
     cister
    -0.49
     unſ
    -0.49
     unes
    -0.49
     consig
    -0.49
     parter
    -0.49
    POSITIVE LOGITS
     progress
    0.61
     adoption
    0.60
     prestazioni
    0.57
     progrès
    0.57
     diagnostic
    0.55
     relazioni
    0.55
     progresses
    0.54
     progressed
    0.53
     réglable
    0.52
     Diagnostic
    0.52
    Act Density 0.319%

    No Known Activations