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

    Neuronpedia

    INDEX
    Explanations

    references to intervention strategies and implementations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPATH
    -0.76
     Feld
    -0.70
    isbury
    -0.69
     Bohn
    -0.68
    erencia
    -0.64
    ftagPool
    -0.63
     Amad
    -0.63
     Chartres
    -0.61
    createCell
    -0.60
    olsom
    -0.59
    POSITIVE LOGITS
     manoeuvre
    0.91
     measures
    0.91
     initiatives
    0.90
    ToAction
    0.89
     programmes
    0.86
    +#+#
    0.86
    Initiative
    0.86
     initiative
    0.85
     MEASURES
    0.85
    verwijspagina
    0.85
    Act Density 0.105%

    No Known Activations