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

    Neuronpedia

    INDEX
    Explanations

    action-related verbs and phrases indicating movement or escape

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    byter
    -0.66
    hig
    -0.64
    etus
    -0.63
    amaru
    -0.62
    ongyang
    -0.62
    milo
    -0.62
     oun
    -0.60
    trump
    -0.60
    arate
    -0.60
    untu
    -0.59
    POSITIVE LOGITS
     leash
    0.78
     bandwagon
    0.76
    iveness
    0.70
     Reloaded
    0.69
    ousel
    0.69
     lookout
    0.67
     charger
    0.66
    steps
    0.66
     doorstep
    0.66
     island
    0.66
    Act Density 0.038%

    No Known Activations