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

    Neuronpedia

    INDEX
    Explanations

    phrases that express subjective experiences and personal reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plenty
    -0.18
     indeed
    -0.17
     tomorrow
    -0.17
     may
    -0.16
     might
    -0.15
     Plenty
    -0.15
     hopefully
    -0.15
    alar
    -0.15
     Indeed
    -0.15
     already
    -0.14
    POSITIVE LOGITS
     somehow
    0.41
     Somehow
    0.27
     seem
    0.23
     sanki
    0.22
     somew
    0.22
     seemed
    0.21
     seems
    0.21
     inexp
    0.21
     seeming
    0.20
     myster
    0.20
    Act Density 0.144%

    No Known Activations