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

    Neuronpedia

    INDEX
    Explanations

    present tense verbs indicating states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themselves
    -0.93
    themselves
    -0.75
     themſelves
    -0.73
     were
    -0.60
    selves
    -0.60
     are
    -0.59
    felves
    -0.59
     Agamemnon
    -0.59
    astéroïdes
    -0.58
     ――――――――
    -0.57
    POSITIVE LOGITS
     []:
    0.77
    itself
    0.62
     stuff
    0.55
     itself
    0.51
    kreises
    0.50
     réduite
    0.49
     Concentr
    0.49
    Sams
    0.49
    zysta
    0.48
     usted
    0.48
    Act Density 0.202%

    No Known Activations