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

    Neuronpedia

    INDEX
    Explanations

    words related to being forgotten or overlooked

    oai_token-act-pair · gpt-3.5-turbo

    terms related to things that are neglected or not remembered

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alty
    -0.83
    uliffe
    -0.81
    ramid
    -0.81
    aton
    -0.80
    ijing
    -0.80
    ayne
    -0.80
    ebus
    -0.79
    otaur
    -0.78
    ership
    -0.73
     brim
    -0.72
    POSITIVE LOGITS
     forgotten
    0.86
     Sparkle
    0.84
     Memories
    0.83
    ãĤī
    0.81
     Unch
    0.76
     Voices
    0.75
     Hero
    0.74
    ãĤĤ
    0.73
    UF
    0.71
     Wem
    0.70
    Act Density 0.028%

    No Known Activations