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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal feelings or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of first-person pronouns and related verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lyme
    -0.72
     Commerce
    -0.71
     Alexa
    -0.68
     Clover
    -0.68
     Paste
    -0.66
     Minecraft
    -0.66
     Academy
    -0.65
     Twilight
    -0.64
     XX
    -0.63
     Annotations
    -0.62
    POSITIVE LOGITS
    ldon
    1.18
    zbollah
    1.12
    ngth
    1.00
    ETF
    0.96
    eks
    0.92
    entin
    0.91
    alyst
    0.90
    andum
    0.89
    xtap
    0.88
    Gov
    0.87
    Act Density 0.178%

    No Known Activations