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

    Neuronpedia

    INDEX
    Explanations

    references to methods or ways of achieving something

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

    one way to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    usitis
    -0.56
    Autoritní
    -0.55
     anún
    -0.51
     gustaMe
    -0.50
    cillor
    -0.49
    acchi
    -0.49
     queſta
    -0.48
     increí
    -0.48
     lenker
    -0.48
     Bewußt
    -0.48
    POSITIVE LOGITS
     Way
    0.63
    Way
    0.57
    irectional
    0.54
     WAY
    0.51
     way
    0.50
    way
    0.49
    directional
    0.42
     Ways
    0.40
    Direction
    0.39
    somewhere
    0.39
    Act Density 0.010%

    No Known Activations