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

    Neuronpedia

    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turbo

    social media handles and usernames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ninth
    -0.84
     Boo
    -0.81
     Tone
    -0.80
     Direction
    -0.79
     Orient
    -0.77
     CSI
    -0.77
     Instr
    -0.76
     Tenth
    -0.76
     Eighth
    -0.74
     Habit
    -0.74
    POSITIVE LOGITS
    olson
    1.32
    podcast
    1.31
    aylor
    1.26
    iverpool
    1.25
    opez
    1.24
    maxwell
    1.24
    cott
    1.22
    abama
    1.22
    music
    1.22
    ames
    1.22
    Act Density 0.150%

    No Known Activations