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

    Neuronpedia

    INDEX
    Explanations

    mathematical or logical structures and formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.66
    ]--;
    -0.65
     Normdatei
    -0.63
     relâche
    -0.61
    EndContext
    -0.58
    Distribuzione
    -0.57
     Paglinawan
    -0.57
     Italijani
    -0.57
     ويكيميديا
    -0.55
    WithMany
    -0.55
    POSITIVE LOGITS
    цездатний
    0.56
    tvguidetime
    0.53
     smooth
    0.49
     Pellegrini
    0.46
    íncipe
    0.46
     ple
    0.46
    OnInit
    0.45
     emotion
    0.45
    Denomin
    0.45
    styled
    0.45
    Act Density 0.163%

    No Known Activations