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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.65
     kasarigan
    -0.57
    UR
    -0.57
    Addo
    -0.56
     ECS
    -0.56
     Ignatius
    -0.54
    In
    -0.53
     blad
    -0.51
    Open
    -0.51
    äischen
    -0.51
    POSITIVE LOGITS
    [++
    0.86
     if
    0.84
    WireFormatLite
    0.83
    FTFY
    0.80
    `;
    0.76
    setVerticalGroup
    0.73
     unless
    0.73
    unless
    0.71
    etheless
    0.70
    ]--;
    0.70
    Act Density 0.144%

    No Known Activations