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

    Neuronpedia

    INDEX
    Explanations

    occurrences of personal reflection and emotional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tison
    -0.59
     }}"></
    -0.57
    TableBody
    -0.55
     heard
    -0.55
     dacht
    -0.53
    AndEndTag
    -0.52
    transQ
    -0.52
    TagHelper
    -0.52
    lesh
    -0.52
    heard
    -0.52
    POSITIVE LOGITS
     admire
    1.03
     admiring
    1.02
     gaw
    1.00
     marvel
    0.92
     ooh
    0.89
     gaze
    0.89
     admires
    0.88
     admired
    0.87
     admiration
    0.82
     stare
    0.81
    Act Density 0.291%

    No Known Activations