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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment or critique in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stakes
    -0.16
    akash
    -0.15
    »¿
    -0.15
    hydr
    -0.14
    ÑĤого
    -0.14
     Briggs
    -0.14
    imei
    -0.14
    inflate
    -0.14
    uids
    -0.14
    overy
    -0.13
    POSITIVE LOGITS
    ja
    0.17
    हर
    0.15
    etro
    0.15
    çĢ
    0.14
    chin
    0.14
     równ
    0.14
    ville
    0.14
    liner
    0.14
     ÎijÏĢ
    0.13
    हल
    0.13
    Act Density 0.164%

    No Known Activations