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

    Neuronpedia

    INDEX
    Explanations

    references to professional careers and career paths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -0.17
    ose
    -0.16
    isson
    -0.15
     occasion
    -0.15
    qid
    -0.15
    chin
    -0.15
    tures
    -0.15
    ayo
    -0.14
     crew
    -0.14
    or
    -0.14
    POSITIVE LOGITS
    -long
    0.23
     path
    0.19
    -span
    0.18
    -ending
    0.18
    -threatening
    0.18
    trajectory
    0.18
    istically
    0.17
     trajectory
    0.17
     traj
    0.16
    .Cryptography
    0.16
    Act Density 0.020%

    No Known Activations