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

    Neuronpedia

    INDEX
    Explanations

    Twitter usernames with associated dates

    oai_token-act-pair · gpt-3.5-turbo

    references to social media handles or usernames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Takeru
    -0.92
     metic
    -0.81
    ortunately
    -0.74
     tampering
    -0.72
     conflic
    -0.72
     Skydragon
    -0.69
    ailability
    -0.67
    aditional
    -0.67
     Dimensions
    -0.67
     detrim
    -0.67
    POSITIVE LOGITS
    Jacob
    0.76
    obj
    0.75
    )"
    0.72
    rb
    0.71
    ãĥ
    0.71
    ename
    0.70
    Ford
    0.69
    Brend
    0.68
    Fred
    0.67
    Fla
    0.66
    Act Density 0.044%

    No Known Activations