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

    Neuronpedia

    INDEX
    Explanations

    mentions of "epilogue" or prefixes/suffixes involving "epi-" such as "episodic" or "epidemic"

    oai_token-act-pair · gpt-3.5-turbo

    words and terms associated with episodic memory and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aughs
    -0.79
     srfAttach
    -0.72
    boxing
    -0.71
    erness
    -0.66
    ikuman
    -0.65
    boa
    -0.64
    çĦ
    -0.63
    erest
    -0.63
    ictionary
    -0.61
    zbek
    -0.61
    POSITIVE LOGITS
    phrine
    1.00
    odic
    0.87
    etheus
    0.77
    ©¶æ
    0.74
    aic
    0.74
    umatic
    0.74
    ascript
    0.73
    Ö¼
    0.70
    OPLE
    0.69
    oine
    0.69
    Act Density 0.079%

    No Known Activations