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

    Neuronpedia

    INDEX
    Explanations

    references to various strategies used in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     berdua
    -0.60
     garantía
    -0.58
     campamento
    -0.57
     explosión
    -0.55
     instalación
    -0.54
     alambre
    -0.54
     recevez
    -0.54
     automne
    -0.54
     detención
    -0.52
     exhibición
    -0.52
    POSITIVE LOGITS
     clutches
    0.62
     tick
    0.62
     clutch
    0.60
     ticked
    0.57
     strategy
    0.56
     Clutch
    0.54
     ctrl
    0.54
     strategies
    0.52
     structured
    0.52
     prop
    0.51
    Act Density 0.230%

    No Known Activations