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

    Neuronpedia

    INDEX
    Explanations

    approximations or estimates expressed with the word "roughly."

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

    approximations and estimates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     препратки
    -0.43
     vær
    -0.43
     scin
    -0.39
     doa
    -0.39
    fvar
    -0.38
    PreExecute
    -0.37
    ändigkeit
    -0.36
    </td>
    -0.36
    ydd
    -0.35
    underset
    -0.35
    POSITIVE LOGITS
     roughly
    1.63
    roughly
    1.53
     Roughly
    1.49
    Rough
    0.75
     broadly
    0.75
     ungefähr
    0.73
    大致
    0.71
     loosely
    0.70
     примерно
    0.70
    およ
    0.68
    Act Density 0.010%

    No Known Activations