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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts related to ethics and moral values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ically
    -0.26
    arp
    -0.18
    368
    -0.16
    andum
    -0.16
    um
    -0.15
    ãĥ¼ãĥĹ
    -0.15
    _TUN
    -0.15
    quires
    -0.14
    зÑĮ
    -0.14
    ©
    -0.14
    POSITIVE LOGITS
    ember
    0.18
    ally
    0.16
    ellite
    0.16
    optera
    0.15
    CSI
    0.15
    ÑģÑĤÑİ
    0.15
    ized
    0.14
    itional
    0.14
    ixin
    0.14
    WD
    0.14
    Act Density 0.091%

    No Known Activations