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

    Neuronpedia

    INDEX
    Explanations

    conditional or contrasting statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelf
    -0.77
    ſelves
    -0.76
     Verfügung
    -0.70
     ویکی‌پدیا
    -0.68
    pondre
    -0.68
    IsContent
    -0.67
     himſelf
    -0.67
    herself
    -0.66
     Cæsar
    -0.66
    -0.66
    POSITIVE LOGITS
     While
    0.92
    While
    0.91
    Though
    0.90
     Though
    0.84
    Whilst
    0.65
    Although
    0.65
    WHILE
    0.65
     Although
    0.64
     though
    0.59
     Whilst
    0.58
    Act Density 0.119%

    No Known Activations