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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating advantages or special features in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukone
    -0.51
     aplicable
    -0.51
    (*
    -0.50
     neler
    -0.47
     demas
    -0.47
    Talon
    -0.46
    stwie
    -0.46
    TextUtils
    -0.45
    oram
    -0.45
     slutt
    -0.45
    POSITIVE LOGITS
     idea
    0.94
     notion
    0.89
     option
    0.84
     concept
    0.79
    SequentialGroup
    0.77
     task
    0.72
    advantage
    0.71
     issue
    0.69
     prospect
    0.69
     ability
    0.68
    Act Density 0.418%

    No Known Activations