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

    Neuronpedia

    INDEX
    Explanations

    concepts related to uniqueness and differentiation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nbsp
    -0.18
     restrictions
    -0.18
    stretch
    -0.17
    anna
    -0.16
     restrict
    -0.16
    stral
    -0.15
    holder
    -0.15
     stretch
    -0.15
    itations
    -0.15
     restricting
    -0.15
    POSITIVE LOGITS
    ively
    0.55
    iveness
    0.37
    ive
    0.34
    ivist
    0.26
    ives
    0.25
    IVE
    0.24
    ivism
    0.24
    IVEN
    0.21
    ible
    0.20
    iven
    0.19
    Act Density 0.084%

    No Known Activations