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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce contrasting ideas or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rope
    -0.48
    ázaro
    -0.47
    PDO
    -0.47
    újo
    -0.46
    Superview
    -0.46
     iVar
    -0.45
    ]--;
    -0.45
     Piso
    -0.45
     puberty
    -0.44
    feira
    -0.44
    POSITIVE LOGITS
    rungsseite
    0.90
    而是
    0.80
     chi̍t
    0.80
     برانيه
    0.79
    DockStyle
    0.74
     sondern
    0.73
    HostException
    0.72
    iyle
    0.71
     hanem
    0.69
     Instead
    0.68
    Act Density 0.278%

    No Known Activations