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

    Neuronpedia

    INDEX
    Explanations

    probabilities or likelihoods associated with statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "because," "should," or similar words after "probably."

    np_acts-logits-general · gemini-2.0-flash

    probability and reasoning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Z
    -0.49
    D
    -0.49
     Ches
    -0.47
    Z
    -0.47
    PART
    -0.46
    R
    -0.46
     Zane
    -0.45
    Bos
    -0.44
    CHM
    -0.44
     Alexandra
    -0.44
    POSITIVE LOGITS
     propOrder
    1.03
    bably
    0.93
    vably
    0.91
    Aiheesta
    0.90
    ########.
    0.85
    abestanden
    0.85
    المناصب
    0.85
    ]-->
    0.84
    OGND
    0.82
    IntoConstraints
    0.81
    Act Density 0.072%

    No Known Activations