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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions that indicate presence or return

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lient
    -0.15
     neod
    -0.15
    studio
    -0.14
    ÏħÏĥ
    -0.14
    ANCELED
    -0.14
     -------------------------------------------------------------------------↵
    -0.14
    annabin
    -0.14
    izza
    -0.13
    aldi
    -0.13
     htons
    -0.13
    POSITIVE LOGITS
    gos
    0.22
    INA
    0.16
    338
    0.16
     presente
    0.15
     depart
    0.15
    hdl
    0.15
     blows
    0.15
    osphere
    0.15
     present
    0.15
     go
    0.14
    Act Density 0.023%

    No Known Activations