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

    Neuronpedia

    INDEX
    Explanations

    words indicating approvals, releases, or delivery in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deleg
    -0.70
    brid
    -0.62
    wing
    -0.61
    etric
    -0.60
    ãĥª
    -0.60
    pher
    -0.58
    nton
    -0.58
     divers
    -0.58
    itia
    -0.58
    izontal
    -0.57
    POSITIVE LOGITS
     unbeliev
    0.84
     prominently
    0.84
     unden
    0.80
    netflix
    0.77
    ELF
    0.76
     spontaneously
    0.74
     alongside
    0.73
     smoothly
    0.72
     concurrently
    0.70
    uesday
    0.70
    Act Density 0.118%

    No Known Activations