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

    Neuronpedia

    INDEX
    Explanations

    numbers presented in a specific format: a digit followed by a dash and another digit

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rame
    -0.63
     destro
    -0.61
    agna
    -0.57
    ourt
    -0.57
     forcefully
    -0.57
    TeX
    -0.57
     newsp
    -0.57
    ilic
    -0.57
    legal
    -0.57
    Ħ¢
    -0.56
    POSITIVE LOGITS
    %;
    1.06
     pts
    1.01
    %:
    0.96
    %,
    0.94
     Votes
    0.88
     (-
    0.87
     [+
    0.85
    %-
    0.84
    %
    0.84
     wins
    0.78
    Act Density 0.164%

    No Known Activations