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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing excessive or overwhelming sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     toch
    -0.18
    pu
    -0.17
    map
    -0.17
    ydı
    -0.16
    ry
    -0.16
    st
    -0.16
    мов
    -0.16
    wood
    -0.15
    ÑĢен
    -0.15
    patch
    -0.15
    POSITIVE LOGITS
    led
    0.32
     boot
    0.30
    o
    0.26
    ledo
    0.24
    oot
    0.24
     Boot
    0.23
    oo
    0.22
    gether
    0.21
     much
    0.21
    boot
    0.20
    Act Density 0.022%

    No Known Activations