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

    Neuronpedia

    INDEX
    Explanations

    words related to various forms of the verb "have" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    i
    -0.25
    iya
    -0.20
    ebo
    -0.19
    ece
    -0.17
    udeau
    -0.17
    y
    -0.17
    eel
    -0.17
    ieme
    -0.16
    idon
    -0.16
    रत
    -0.16
    POSITIVE LOGITS
    oir
    0.25
    vy
    0.23
    olution
    0.23
    irtual
    0.22
    vv
    0.22
    on
    0.21
    oxel
    0.20
    est
    0.20
    ski
    0.19
    oice
    0.19
    Act Density 0.036%

    No Known Activations