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

    Neuronpedia

    INDEX
    Explanations

    concepts related to mental frameworks and cognitive processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cox
    -0.15
    ynth
    -0.15
    teil
    -0.15
     aggress
    -0.14
    prov
    -0.14
    ÄĻp
    -0.14
    ync
    -0.14
    agar
    -0.14
    _ABI
    -0.13
    iddi
    -0.13
    POSITIVE LOGITS
     representations
    0.25
     chunk
    0.25
     Chunk
    0.24
    åĬłå·¥
    0.21
     representation
    0.21
    Chunk
    0.20
     cort
    0.20
     chunks
    0.20
    chunk
    0.20
     processing
    0.19
    Act Density 0.018%

    No Known Activations