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

    Neuronpedia

    INDEX
    Explanations

    themes related to societal structures and their potential collapse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ront
    -0.16
    rape
    -0.14
    gboolean
    -0.14
    IMA
    -0.14
    olen
    -0.14
     Podle
    -0.14
    اغ
    -0.14
    æĤł
    -0.13
     VÅ¡
    -0.13
     jumps
    -0.13
    POSITIVE LOGITS
     collapse
    0.57
     collapsing
    0.49
     collapsed
    0.47
     Collapse
    0.47
    -collapse
    0.47
    collapse
    0.46
     collapses
    0.45
     breakdown
    0.44
     collaps
    0.43
     crumbling
    0.43
    Act Density 0.265%

    No Known Activations