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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with tuning in or listening actively

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uster
    -0.19
    ucer
    -0.18
    usters
    -0.17
    ONA
    -0.17
    ona
    -0.15
    rength
    -0.15
    inson
    -0.15
    eyer
    -0.15
    USTER
    -0.14
    imuth
    -0.14
    POSITIVE LOGITS
     fork
    0.24
    isia
    0.23
     Tun
    0.22
     Fork
    0.21
     tuning
    0.19
     forks
    0.19
    eful
    0.19
    fork
    0.19
    NEL
    0.19
     Tune
    0.18
    Act Density 0.012%

    No Known Activations