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

    Neuronpedia

    INDEX
    Explanations

    phrases related to verifying if a user is a human or robot

    oai_token-act-pair · gpt-3.5-turbo

    terms related to verification and user authentication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Guid
    -0.61
     tongues
    -0.60
     bun
    -0.58
    uries
    -0.58
     hig
    -0.58
     Benn
    -0.58
    [/
    -0.55
     Bak
    -0.55
    liam
    -0.55
     assemblies
    -0.54
    POSITIVE LOGITS
    iframe
    0.74
    76561
    0.71
    à¼
    0.69
    ashington
    0.68
    ESE
    0.67
     Flavoring
    0.66
    ENA
    0.66
     anymore
    0.65
    ichick
    0.64
    rina
    0.64
    Act Density 0.013%

    No Known Activations