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

    Neuronpedia

    INDEX
    Explanations

    phrases related to preparation or prior actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arend
    -0.15
    baugh
    -0.15
    ADE
    -0.15
    atto
    -0.15
    gle
    -0.15
    ë¦
    -0.14
     Obs
    -0.14
    enaire
    -0.14
    dac
    -0.14
    dash
    -0.14
    POSITIVE LOGITS
     allem
    0.29
     Ort
    0.25
    her
    0.24
    rang
    0.23
    arl
    0.23
    beh
    0.22
    er
    0.20
    acious
    0.19
    lie
    0.19
     dem
    0.18
    Act Density 0.005%

    No Known Activations