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

    Neuronpedia

    INDEX
    Explanations

    social media and online posts

    oai_token-act-pair · gpt-3.5-turbo

    references to online posts and official statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cause
    -0.79
    .''.
    -0.67
    $.
    -0.60
    animate
    -0.59
    "},"
    -0.58
     outweigh
    -0.55
    depend
    -0.54
    existent
    -0.53
    addons
    -0.53
    ont
    -0.52
    POSITIVE LOGITS
     titled
    0.80
     accompanying
    0.78
     announcing
    0.74
     nutshell
    0.71
     interview
    0.70
     released
    0.70
     dated
    0.68
    idav
    0.68
     published
    0.68
    ,
    0.65
    Act Density 0.176%

    No Known Activations