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

    Neuronpedia

    INDEX
    Explanations

    terms related to investigations that imply potential wrongdoing or misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inan
    -0.17
    uis
    -0.15
    elves
    -0.15
    osy
    -0.15
    bard
    -0.14
    ifen
    -0.14
    coe
    -0.14
    ominator
    -0.14
    稱
    -0.13
    inden
    -0.13
    POSITIVE LOGITS
     Viol
    0.15
    etag
    0.14
    assa
    0.14
    ries
    0.14
    iph
    0.14
    ophobia
    0.14
    avl
    0.14
    _transient
    0.13
     Mixed
    0.13
     Hubbard
    0.13
    Act Density 0.345%

    No Known Activations