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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating agreement or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hym
    -0.72
     Chwiliwch
    -0.65
    AutoresizingMask
    -0.64
    BorderFactory
    -0.62
    $',
    -0.62
     APPEAL
    -0.60
    $.
    -0.59
     externi
    -0.59
    ]?.
    -0.58
     utafitiHapana
    -0.58
    POSITIVE LOGITS
    UpInside
    0.66
    .
    0.60
    zydent
    0.54
    ,
    0.52
    ComponentModel
    0.52
    dersfield
    0.50
    DockStyle
    0.49
    Same
    0.48
    soundcloud
    0.48
     مدر
    0.47
    Act Density 0.078%

    No Known Activations