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

    Neuronpedia

    INDEX
    Explanations

    significant negative phrases related to potential personal losses or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NET
    -0.17
     Net
    -0.16
    iesz
    -0.15
    ere
    -0.15
     net
    -0.15
    jem
    -0.15
     forgotten
    -0.15
    Net
    -0.14
    NET
    -0.14
     church
    -0.14
    POSITIVE LOGITS
    İ
    0.18
    олÑĮкÑĥ
    0.16
    .gdx
    0.15
    /goto
    0.14
    ãĥ
    0.14
    리카
    0.14
    DCALL
    0.14
    castle
    0.14
    벤
    0.14
    ourcem
    0.13
    Act Density 0.285%

    No Known Activations