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

    Neuronpedia

    INDEX
    Explanations

    instances of legal terminology or references to legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.80
    ⟬
    -0.74
     moreover
    -0.72
     ProtoMessage
    -0.71
    RTLD
    -0.68
     inoltre
    -0.64
     Signalez
    -0.64
     nevertheless
    -0.63
     furthermore
    -0.62
     however
    -0.61
    POSITIVE LOGITS
    Every
    0.82
    When
    0.80
    Sometimes
    0.79
    Imagine
    0.79
    Ever
    0.74
    Recently
    0.71
    Cuando
    0.70
    Today
    0.69
    Everyone
    0.68
    During
    0.67
    Act Density 0.458%

    No Known Activations