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

    Neuronpedia

    INDEX
    Explanations

    sentences that describe uncertainty or opinionated remarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ines
    -0.21
    u
    -0.15
    ós
    -0.15
     ir
    -0.15
     Laurent
    -0.14
    rink
    -0.14
     environment
    -0.14
    fin
    -0.14
    oss
    -0.14
    ous
    -0.14
    POSITIVE LOGITS
     cryst
    0.19
    ινÏĮ
    0.16
    ÐIJÑĢÑħÑĸв
    0.15
    issan
    0.15
     iParam
    0.15
     kabil
    0.15
    CKER
    0.14
    ØŃÙĦ
    0.14
    .ibatis
    0.14
    esser
    0.14
    Act Density 0.348%

    No Known Activations