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

    Neuronpedia

    INDEX
    Explanations

    negative terms or phrases relating to lack or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    каÑģ
    -0.16
    landa
    -0.15
    rente
    -0.15
    mente
    -0.14
    ries
    -0.14
    neider
    -0.14
    umd
    -0.14
    uate
    -0.14
    umn
    -0.14
    tools
    -0.14
    POSITIVE LOGITS
    xious
    0.19
    zzle
    0.17
    ire
    0.17
    BLE
    0.17
    okie
    0.17
    isy
    0.17
     longer
    0.17
    oks
    0.16
    çłģ
    0.16
    ork
    0.16
    Act Density 0.062%

    No Known Activations