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

    Neuronpedia

    INDEX
    Explanations

    instances where events from the past continue to have relevance or impact

    oai_token-act-pair · gpt-3.5-turbo

    the word "still" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insula
    -0.72
    ASE
    -0.64
    DI
    -0.61
     Moody
    -0.59
     elimination
    -0.59
     Stim
    -0.58
     Extension
    -0.57
    ufact
    -0.56
     Correction
    -0.55
     Attention
    -0.55
    POSITIVE LOGITS
    birth
    1.27
     retains
    0.94
    born
    0.92
     reeling
    0.86
     haun
    0.84
    ness
    0.78
     exists
    0.78
     manages
    0.78
     retain
    0.78
    heres
    0.77
    Act Density 0.058%

    No Known Activations