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

    Neuronpedia

    INDEX
    Explanations

    the word "additional" and its variations, indicating a focus on supplementary or extra information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogl
    -0.15
    vak
    -0.15
    places
    -0.14
    ÂŃing
    -0.14
    jo
    -0.14
    ifications
    -0.14
    ego
    -0.14
    abilit
    -0.13
    §
    -0.13
    oshi
    -0.13
    POSITIVE LOGITS
    ordinary
    0.22
    endum
    0.21
    /new
    0.21
    ordin
    0.20
    y
    0.20
    /sub
    0.20
    mente
    0.19
    aea
    0.19
    tion
    0.19
    ookie
    0.18
    Act Density 0.029%

    No Known Activations