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

    Neuronpedia

    INDEX
    Explanations

    phrases related to gratitude and positive feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HDR
    -0.15
     magn
    -0.14
    reck
    -0.14
     herr
    -0.13
    296
    -0.13
    peat
    -0.13
    unken
    -0.13
    heed
    -0.13
    oon
    -0.13
    abi
    -0.13
    POSITIVE LOGITS
    pson
    0.18
    icot
    0.16
    NET
    0.15
    acht
    0.14
    distributed
    0.14
    net
    0.14
     distributed
    0.14
    bane
    0.14
     Net
    0.13
     terminal
    0.13
    Act Density 0.007%

    No Known Activations