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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate hierarchical or authoritative relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĽ
    -0.15
    roscope
    -0.15
    loy
    -0.15
    tero
    -0.14
    TEL
    -0.14
    ante
    -0.14
    onda
    -0.14
    orno
    -0.14
    аÑı
    -0.14
    ìķķ
    -0.14
    POSITIVE LOGITS
     gere
    0.16
     ê
    0.15
     vp
    0.14
    оÑĪ
    0.14
    vpn
    0.14
    148
    0.14
    oken
    0.14
     apparel
    0.13
    iere
    0.13
     diverse
    0.13
    Act Density 0.009%

    No Known Activations