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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate presidential titles and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Gear
    -0.16
    Slash
    -0.15
    fos
    -0.15
    oda
    -0.15
    ]=>
    -0.14
    ãĤ¦ãĤ¹
    -0.14
    reflection
    -0.14
    oust
    -0.14
     Summon
    -0.14
    sep
    -0.14
    POSITIVE LOGITS
    vr
    0.21
     PT
    0.17
    obia
    0.15
    _PT
    0.15
     hell
    0.15
    uria
    0.14
     dos
    0.14
    exec
    0.14
     tails
    0.13
    PT
    0.13
    Act Density 0.033%

    No Known Activations