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

    Neuronpedia

    INDEX
    Explanations

    evaluative expressions related to quality and sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anken
    -0.16
    /Dk
    -0.15
    anes
    -0.14
    ãģıãĤī
    -0.14
    á»ģn
    -0.14
    isma
    -0.14
    SelfPermission
    -0.14
    ADM
    -0.14
    nero
    -0.14
    oad
    -0.14
    POSITIVE LOGITS
     indeed
    0.30
     huh
    0.25
    inde
    0.24
     eh
    0.21
     Indeed
    0.19
    Indeed
    0.19
     considering
    0.17
    unar
    0.17
    icker
    0.15
    ooks
    0.15
    Act Density 0.148%

    No Known Activations