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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to negative situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ả
    -0.17
    ãĥ¼ãĥĢ
    -0.15
    edla
    -0.14
     mole
    -0.14
     elig
    -0.14
    tape
    -0.14
    :animated
    -0.14
    itur
    -0.14
    ä¸ĺ
    -0.14
    DX
    -0.13
    POSITIVE LOGITS
    олÑĮ
    0.17
    acen
    0.15
    ices
    0.15
    ноÑģÑıÑĤ
    0.14
    Correction
    0.13
     BroadcastReceiver
    0.13
    372
    0.13
    lices
    0.13
    AKE
    0.13
    aycast
    0.13
    Act Density 0.303%

    No Known Activations