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

    Neuronpedia

    INDEX
    Explanations

    negative expressions regarding quality or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    дов
    -0.15
    ÏģÏį
    -0.15
    eniable
    -0.14
    ấp
    -0.14
    dale
    -0.14
    ilton
    -0.14
    sel
    -0.13
    deo
    -0.13
    ague
    -0.13
     somewhat
    -0.13
    POSITIVE LOGITS
     TOO
    0.21
     Sweat
    0.19
     necessarily
    0.18
     sweat
    0.18
    wor
    0.18
    .problem
    0.17
    éĹ®é¢ĺ
    0.16
    åķıé¡Į
    0.16
     too
    0.16
     Wor
    0.16
    Act Density 0.138%

    No Known Activations