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

    Neuronpedia

    INDEX
    Explanations

    instances of forgetting or failure to remember something

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to forgetting or memory lapses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amen
    -0.74
    Parser
    -0.73
    Builder
    -0.73
    osion
    -0.70
    berus
    -0.64
    atform
    -0.64
    Released
    -0.64
    cheat
    -0.64
    ourke
    -0.63
    INC
    -0.62
    POSITIVE LOGITS
    fulness
    1.25
    fully
    1.03
    ful
    1.03
    table
    0.84
     Realms
    0.76
    noon
    0.75
    theless
    0.73
     about
    0.72
     remembered
    0.68
    touch
    0.67
    Act Density 0.035%

    No Known Activations