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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the idea of irrelevance or indifference to circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hawthorn
    -0.54
    dafrika
    -0.52
     delin
    -0.52
     cref
    -0.52
     Hyde
    -0.51
    IGraphics
    -0.51
    จึง
    -0.51
    umuz
    -0.49
    ̈́
    -0.49
    нє
    -0.49
    POSITIVE LOGITS
    regardless
    1.28
     regardless
    1.26
     Regardless
    1.15
    Regardless
    1.09
     irrespective
    1.05
    dientemente
    1.00
     Infórmanos
    0.95
    importe
    0.93
     whether
    0.91
    hichever
    0.89
    Act Density 0.111%

    No Known Activations