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

    Neuronpedia

    INDEX
    Explanations

    phrases related to product features and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.81
     przecież
    -0.59
    不但
    -0.55
     endwhile
    -0.55
    isSuccessful
    -0.53
    BIÉN
    -0.53
    eloma
    -0.52
     jedenfalls
    -0.51
    pso
    -0.51
     wenigstens
    -0.51
    POSITIVE LOGITS
     slightly
    1.75
    slightly
    1.60
     somewhat
    1.60
     Slightly
    1.57
     trochu
    1.47
    Slightly
    1.44
    somewhat
    1.42
     Somewhat
    1.42
     biraz
    1.41
    少々
    1.37
    Act Density 0.473%

    No Known Activations