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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal memories and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ildo
    -0.20
    ollo
    -0.16
    ñana
    -0.16
    ewis
    -0.15
    olie
    -0.15
    lops
    -0.15
    ieu
    -0.15
    Printf
    -0.15
    amber
    -0.14
    erez
    -0.14
    POSITIVE LOGITS
     exact
    0.21
    è®°
    0.21
     memory
    0.21
    memory
    0.20
     Memory
    0.20
    Exact
    0.19
     recall
    0.19
     remember
    0.19
     remembers
    0.19
     remembered
    0.19
    Act Density 0.144%

    No Known Activations