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

    Neuronpedia

    INDEX
    Explanations

    concepts and phrases indicating future progress or development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ospel
    -0.16
    imits
    -0.16
    åĻ¨
    -0.14
    quoi
    -0.14
    FFECT
    -0.14
    alist
    -0.14
    heit
    -0.14
    eneric
    -0.14
    idable
    -0.14
    ync
    -0.14
    POSITIVE LOGITS
    -generation
    0.38
    -door
    0.36
     few
    0.31
     generation
    0.30
    -gen
    0.28
    -best
    0.28
    door
    0.27
     logical
    0.25
    /current
    0.25
    generation
    0.24
    Act Density 0.048%

    No Known Activations