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

    Neuronpedia

    INDEX
    Explanations

    instances of bias and its applications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bitterness
    -0.21
    ase
    -0.20
    esi
    -0.19
    esor
    -0.18
    abelle
    -0.17
    bounded
    -0.16
    _browser
    -0.16
     broader
    -0.16
    ESSAGES
    -0.15
    便
    -0.15
    POSITIVE LOGITS
    .gdx
    0.26
    jamin
    0.25
    quets
    0.25
    antine
    0.21
     latter
    0.20
    =B
    0.19
    friend
    0.19
    iful
    0.19
    irectional
    0.18
    emer
    0.18
    Act Density 1.641%

    No Known Activations