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

    Neuronpedia

    INDEX
    Explanations

    the word "Se" in different contexts, often related to sequences or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.19
    ingham
    -0.19
    sh
    -0.17
    land
    -0.17
    secure
    -0.16
    loan
    -0.15
    sets
    -0.15
    res
    -0.15
    set
    -0.15
    so
    -0.15
    POSITIVE LOGITS
    bastian
    0.24
    bast
    0.22
    attle
    0.19
    infeld
    0.19
    URITY
    0.19
    lected
    0.18
    ITHER
    0.18
    edy
    0.17
    eed
    0.17
    veral
    0.17
    Act Density 0.022%

    No Known Activations