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

    Neuronpedia

    INDEX
    Explanations

    terms related to new developments or innovations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rien
    -0.19
    furt
    -0.15
    ultz
    -0.15
    inal
    -0.15
    ittel
    -0.14
    ìľ¡
    -0.14
    eggies
    -0.14
    éĢĶ
    -0.14
    _macros
    -0.14
    ãĥ¼ãĥł
    -0.14
    POSITIVE LOGITS
     Milo
    0.15
     past
    0.15
    íĨ
    0.14
    ailer
    0.14
     =č↵
    0.14
     Horton
    0.14
     atIndex
    0.13
    dG
    0.13
     esac
    0.13
     bur
    0.13
    Act Density 0.015%

    No Known Activations