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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize uniqueness or specific qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arken
    -0.18
    urge
    -0.16
    inel
    -0.15
    andal
    -0.15
    RACT
    -0.15
    اء
    -0.15
    encer
    -0.15
    onder
    -0.15
    endas
    -0.15
    омеÑĢ
    -0.15
    POSITIVE LOGITS
    ities
    0.21
    ily
    0.20
    ity
    0.19
    mente
    0.19
    ty
    0.19
    timing
    0.19
    istically
    0.18
    tons
    0.17
    ized
    0.17
    ally
    0.16
    Act Density 0.021%

    No Known Activations