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

    Neuronpedia

    INDEX
    Explanations

    references to far-right or extremist ideologies and movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Solitaire
    -0.84
     Puzzles
    -0.82
     Scrib
    -0.77
     Creator
    -0.75
     Phi
    -0.74
     Lock
    -0.71
     Compass
    -0.69
     Tags
    -0.69
     Revolution
    -0.68
     Hyde
    -0.68
    POSITIVE LOGITS
    reaching
    1.39
    ranging
    1.25
    sighted
    1.24
    fetched
    1.24
    eyed
    1.10
    forward
    1.07
    range
    1.03
    distance
    1.02
    spread
    1.01
    backed
    1.00
    Act Density 0.009%

    No Known Activations