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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a location or foundation for various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ksam
    -0.18
    ship
    -0.16
    sel
    -0.15
    vit
    -0.15
    uset
    -0.15
    ruit
    -0.14
    aping
    -0.14
    sing
    -0.14
    .general
    -0.14
    elmet
    -0.13
    POSITIVE LOGITS
     upon
    0.19
    upon
    0.17
    Upon
    0.14
     grounds
    0.14
    -base
    0.14
    ento
    0.14
    chain
    0.14
    PJ
    0.13
    arry
    0.13
    ugg
    0.13
    Act Density 0.036%

    No Known Activations