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

    Neuronpedia

    INDEX
    Explanations

    pronouns that refer to objects or subjects in the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wet
    -0.15
    elsey
    -0.15
    TEMPL
    -0.14
    кÑĥ
    -0.14
    OLON
    -0.14
     LIABLE
    -0.14
    ugen
    -0.14
    chema
    -0.14
     Eisen
    -0.14
    494
    -0.14
    POSITIVE LOGITS
    Å¡tÄĽ
    0.16
    iner
    0.15
    udy
    0.15
    íı¬
    0.15
    esser
    0.15
    idar
    0.14
    StackNavigator
    0.14
    itrust
    0.13
    anner
    0.13
    ÑĨин
    0.13
    Act Density 0.331%

    No Known Activations