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

    Neuronpedia

    INDEX
    Explanations

    words or phrases followed by "referred to as"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate alternative names or terms for something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iem
    -0.67
    olitics
    -0.66
     exploited
    -0.65
    ////////////////////////////////
    -0.62
    oval
    -0.62
    eland
    -0.62
    PLIED
    -0.61
     ende
    -0.61
    reci
    -0.60
     stoked
    -0.60
    POSITIVE LOGITS
    enance
    0.74
    ript
    0.72
     phrases
    0.68
    =\"
    0.65
     initials
    0.65
    å¯
    0.65
     pronouns
    0.65
    acht
    0.64
    gars
    0.64
     them
    0.63
    Act Density 0.048%

    No Known Activations