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

    Neuronpedia

    INDEX
    Explanations

    terms related to preparations, processes, and functions associated with various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hypers
    -0.15
    hud
    -0.14
     hinges
    -0.14
     hashed
    -0.14
    /hash
    -0.13
    र
    -0.13
    ioxide
    -0.13
    ÅĻes
    -0.13
     hinge
    -0.13
     hasher
    -0.13
    POSITIVE LOGITS
    -he
    0.73
     HE
    0.71
    he
    0.67
    _he
    0.66
    HE
    0.62
     He
    0.59
    He
    0.58
    .he
    0.54
    _HE
    0.54
     he
    0.49
    Act Density 0.210%

    No Known Activations