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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to opposition or being against something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #
    -0.16
    /testify
    -0.16
    ican
    -0.14
    akis
    -0.14
    ai
    -0.14
    одÑĥ
    -0.14
    panies
    -0.13
    odu
    -0.13
    berger
    -0.13
    stag
    -0.13
    POSITIVE LOGITS
    (er
    0.15
    -in
    0.15
    inue
    0.14
    iphery
    0.14
    ụn
    0.14
    uild
    0.14
    -
    0.14
    -through
    0.14
    ilter
    0.14
    ONTAL
    0.14
    Act Density 0.187%

    No Known Activations