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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate significant actions or states of being in relation to existence and presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertos
    -0.14
     Kir
    -0.14
     Kash
    -0.14
    kir
    -0.14
     Reverse
    -0.13
    egal
    -0.13
    reverse
    -0.13
    orent
    -0.13
    rx
    -0.13
    ution
    -0.13
    POSITIVE LOGITS
    zell
    0.16
    ume
    0.15
    ÐĶÐļ
    0.15
    нем
    0.14
     ninh
    0.14
    oner
    0.14
    okie
    0.14
    enko
    0.14
    onna
    0.13
    _TI
    0.13
    Act Density 0.011%

    No Known Activations