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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal feelings of amazement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    i
    -0.23
    iode
    -0.20
    illac
    -0.17
    l
    -0.17
    er
    -0.16
    o
    -0.16
    lus
    -0.15
    abouts
    -0.15
    thalm
    -0.15
    oze
    -0.15
    POSITIVE LOGITS
    putation
    0.24
    oral
    0.23
    ends
    0.22
    assing
    0.22
    enable
    0.22
    ply
    0.22
    orph
    0.21
    iable
    0.21
    ending
    0.20
    icus
    0.19
    Act Density 0.011%

    No Known Activations