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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social issues and ideologies

    oai_token-act-pair · gpt-3.5-turbo

    indications of causality or significant changes in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilar
    -0.78
    noticed
    -0.66
    USS
    -0.65
    ebted
    -0.63
     regretted
    -0.63
    ONDON
    -0.61
    OA
    -0.60
     hairs
    -0.58
    Sus
    -0.58
     ambitious
    -0.58
    POSITIVE LOGITS
     ALWAYS
    0.83
     abound
    0.83
     flourish
    0.82
     dictate
    0.82
     everywhere
    0.80
     perv
    0.78
     trump
    0.77
     always
    0.73
     democrat
    0.72
    always
    0.70
    Act Density 0.424%

    No Known Activations