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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "apology" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bụi
    -0.16
    snapshot
    -0.15
    μη
    -0.14
    DEVICE
    -0.14
    eden
    -0.14
    طاÙĨ
    -0.14
    owler
    -0.14
     Faith
    -0.14
    //===
    -0.14
    venes
    -0.13
    POSITIVE LOGITS
    pear
    0.32
    pliance
    0.32
    ologies
    0.31
    ocalyptic
    0.31
    erture
    0.29
    portion
    0.29
    ology
    0.26
    PEAR
    0.25
    ologia
    0.25
    olog
    0.24
    Act Density 0.018%

    No Known Activations