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

    Neuronpedia

    INDEX
    Explanations

    questions regarding preferences or desires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words expressing desire, preference, or willingness (like "would like," "want," "wish").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.76
     ligiloj
    -0.59
    <?
    -0.59
     Infórmanos
    -0.55
    richTextPanel
    -0.55
    ArrowToggle
    -0.54
     propOrder
    -0.51
     Exacts
    -0.51
     nakalista
    -0.50
     compositeur
    -0.49
    POSITIVE LOGITS
     make
    0.94
     take
    0.86
     give
    0.84
     be
    0.84
     bring
    0.79
     achieve
    0.77
     get
    0.76
     create
    0.75
     apply
    0.75
     perform
    0.75
    Act Density 0.054%

    No Known Activations