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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs that describe depth and breadth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.60
    ьаж
    -0.54
     espor
    -0.51
    évaluateur
    -0.51
    انيف
    -0.51
     ModelExpression
    -0.48
     Yugoslavia
    -0.48
     переписи
    -0.47
     Curitiba
    -0.46
    DataPropertyName
    -0.46
    POSITIVE LOGITS
     deepest
    1.16
     deepen
    1.15
     deeper
    1.11
     deep
    1.10
     depth
    1.07
     deepened
    1.06
     deepening
    1.05
     Deeper
    1.02
     Depth
    0.99
    deep
    0.99
    Act Density 0.404%

    No Known Activations