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

    Neuronpedia

    INDEX
    Explanations

    phrases describing planning or coordinating activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Evidently
    -0.57
     palmar
    -0.54
     SEDS
    -0.54
     masts
    -0.54
     短发
    -0.53
    modb
    -0.52
    Datuak
    -0.52
    $.}
    -0.51
    🏾
    -0.51
     &&
    -0.50
    POSITIVE LOGITS
     memang
    0.66
     dunno
    0.64
     nampak
    0.59
     sebab
    0.56
     takut
    0.56
     bayar
    0.56
     oso
    0.56
     Rm
    0.55
     Liao
    0.54
     cannot
    0.53
    Act Density 0.205%

    No Known Activations