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

    Neuronpedia

    INDEX
    Explanations

    phrases related to consent and information release

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     belts
    -0.15
     Cole
    -0.15
    ©
    -0.14
    éĻµ
    -0.14
    itt
    -0.14
    ering
    -0.14
    ffi
    -0.14
    ort
    -0.14
    utt
    -0.13
     cole
    -0.13
    POSITIVE LOGITS
    ota
    0.18
    alic
    0.17
    amma
    0.17
    /ag
    0.16
     Braun
    0.16
     tac
    0.15
    odzi
    0.15
    agus
    0.14
    ãĥĭãĥĥãĤ¯
    0.14
    lew
    0.14
    Act Density 0.010%

    No Known Activations