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

    Neuronpedia

    INDEX
    Explanations

    temporal references and indicators of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yte
    -0.16
    c
    -0.15
    Compat
    -0.14
     Wag
    -0.14
     Bone
    -0.14
     tub
    -0.14
    ammen
    -0.14
     localVar
    -0.13
    b
    -0.13
    apphire
    -0.13
    POSITIVE LOGITS
    cmds
    0.17
    -scalable
    0.15
    ilim
    0.15
    ahy
    0.15
    iddle
    0.15
    ħn
    0.14
    ifetime
    0.14
    мена
    0.14
    xmm
    0.14
    875
    0.14
    Act Density 0.296%

    No Known Activations