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

    Neuronpedia

    INDEX
    Explanations

    terms related to tuning and adjustments in a systematic or technical context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    tshell
    -0.85
     hObject
    -0.84
    StoreMessageInfo
    -0.81
    Mathias
    -0.81
     nakalista
    -0.80
     Mathias
    -0.79
    Sucesor
    -0.79
    MethodType
    -0.78
    Abitanti
    -0.75
     Merr
    -0.74
    POSITIVE LOGITS
     tuned
    1.52
     TUN
    1.52
     tune
    1.50
     tuning
    1.41
     Tune
    1.38
     Tunes
    1.38
    tune
    1.36
    TUN
    1.36
    Tuning
    1.36
     Tuning
    1.35
    Act Density 0.010%

    No Known Activations