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

    Neuronpedia

    INDEX
    Explanations

    words or names related to specific characters or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aft
    -0.17
    chin
    -0.16
    cen
    -0.16
    i
    -0.15
    engin
    -0.15
    opoulos
    -0.15
    camp
    -0.15
    onte
    -0.15
    d
    -0.15
    ence
    -0.15
    POSITIVE LOGITS
    erals
    0.22
    iversit
    0.21
    ghi
    0.21
    erable
    0.20
    iversal
    0.20
    ächst
    0.20
    cheon
    0.20
    iverse
    0.19
    iversity
    0.19
    lap
    0.19
    Act Density 0.080%

    No Known Activations