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

    Neuronpedia

    INDEX
    Explanations

    timestamps indicating times for events or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mansion
    -0.17
    chop
    -0.15
    s
    -0.15
    ulner
    -0.14
    eteor
    -0.14
    ri
    -0.13
    Å¡li
    -0.13
     Mons
    -0.13
     metres
    -0.13
    inati
    -0.13
    POSITIVE LOGITS
    pm
    0.19
    PM
    0.19
     pm
    0.17
     PM
    0.17
    mtree
    0.15
    _PM
    0.15
    ataire
    0.15
    ÏĢη
    0.15
    andest
    0.15
    _pm
    0.15
    Act Density 0.009%

    No Known Activations