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

    Neuronpedia

    INDEX
    Explanations

    illustrations and examples that enhance understanding and clarity in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DT
    -0.16
    adx
    -0.16
    amel
    -0.15
    kas
    -0.15
    ardin
    -0.14
    .ptr
    -0.14
    åIJ¹
    -0.14
    brace
    -0.13
    736
    -0.13
    ine
    -0.13
    POSITIVE LOGITS
     convey
    0.39
     conveying
    0.30
    communic
    0.28
     communicate
    0.28
     conveyed
    0.27
     Communic
    0.27
     communicator
    0.26
     communicating
    0.25
     communicated
    0.24
     communicates
    0.24
    Act Density 0.141%

    No Known Activations