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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating correctness or suitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     secondly
    -0.61
    RenderAtEndOf
    -0.59
    idać
    -0.59
     ReactDOM
    -0.59
    myself
    -0.56
    raszam
    -0.56
    Myself
    -0.55
     SqlCommand
    -0.55
     ailleurs
    -0.55
    ньому
    -0.55
    POSITIVE LOGITS
     appropriate
    1.05
    appropriate
    0.89
     correct
    0.88
     odpowied
    0.87
     suitable
    0.85
     proper
    0.84
    Appropriate
    0.83
     juiste
    0.81
     richtigen
    0.79
     wrong
    0.78
    Act Density 0.104%

    No Known Activations