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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues, opinions, and beliefs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating consequences and opinions related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è£ħ
    -0.80
    ONSORED
    -0.75
    ħĭ
    -0.73
    soDeliveryDate
    -0.68
    ovember
    -0.67
    uthor
    -0.66
    ãĤ´ãĥ³
    -0.66
    Hack
    -0.65
    URR
    -0.63
    TION
    -0.62
    POSITIVE LOGITS
     whereas
    0.79
     regardless
    0.77
    they
    0.72
     THEY
    0.71
    selves
    0.70
     beware
    0.70
     They
    0.69
    often
    0.69
    sometimes
    0.68
     they
    0.67
    Act Density 0.960%

    No Known Activations