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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or official notifications

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to property damage and personal safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.96
    ĸļ
    -0.85
    gypt
    -0.77
    isen
    -0.74
     Leilan
    -0.73
    ascus
    -0.72
     neighb
    -0.70
    agar
    -0.70
    igans
    -0.68
    iga
    -0.67
    POSITIVE LOGITS
    Ability
    0.77
    BUG
    0.75
    Whereas
    0.68
    Users
    0.68
    APS
    0.68
    amazon
    0.67
    Reporting
    0.67
    Optional
    0.66
    Effective
    0.66
    Developer
    0.66
    Act Density 0.380%

    No Known Activations