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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leaving, abandonment, and isolation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kel
    -0.16
    igy
    -0.16
     kept
    -0.16
    wang
    -0.15
    ácil
    -0.14
    ·æĸ°
    -0.14
     Keeping
    -0.14
    utto
    -0.13
     caucus
    -0.13
    ìĿ´ì§Ģ
    -0.13
    POSITIVE LOGITS
     behind
    0.22
     Behind
    0.20
     aside
    0.19
    beh
    0.18
    Behind
    0.17
    à¹Ħว
    0.17
    élé
    0.17
    velt
    0.16
     open
    0.16
     blank
    0.15
    Act Density 0.063%

    No Known Activations