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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence or absence of species or elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sh
    -0.21
    tron
    -0.18
    sp
    -0.17
    torch
    -0.16
    sw
    -0.16
    lick
    -0.16
    owie
    -0.15
    edes
    -0.15
    ars
    -0.15
    spi
    -0.14
    POSITIVE LOGITS
    entially
    0.19
     Presence
    0.19
    Presence
    0.19
    ential
    0.19
    presence
    0.19
    iment
    0.19
     presence
    0.19
    گاÙĩ
    0.18
     Mori
    0.18
    onym
    0.17
    Act Density 0.035%

    No Known Activations