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

    Neuronpedia

    INDEX
    Explanations

    terms related to semi-structured or semi-permanent items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iability
    -0.15
    atitude
    -0.14
    @student
    -0.14
    fully
    -0.14
     semiclass
    -0.14
    isContained
    -0.14
    ullo
    -0.14
    ÏĦια
    -0.13
    halt
    -0.13
     Curtain
    -0.13
    POSITIVE LOGITS
    annual
    0.22
    -automatic
    0.22
    permanent
    0.20
    antically
    0.20
    ãĥĬãĥ¼
    0.19
     permanent
    0.19
    /full
    0.19
     transparent
    0.19
    -finals
    0.19
    -aut
    0.18
    Act Density 0.010%

    No Known Activations