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

    Neuronpedia

    INDEX
    Explanations

    terms related to benchmarks and assessments in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ase
    -0.21
     bitterness
    -0.20
    abelle
    -0.19
    esi
    -0.19
     broader
    -0.18
    esor
    -0.15
     breadth
    -0.15
    -0.15
    å£ģ
    -0.15
    rit
    -0.15
    POSITIVE LOGITS
    jamin
    0.28
    .gdx
    0.25
    quets
    0.23
    emer
    0.20
    umen
    0.19
    iful
    0.18
    antine
    0.18
    friend
    0.18
     Aires
    0.18
    esda
    0.18
    Act Density 2.491%

    No Known Activations