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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant measurements and evaluations within scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dech
    -0.17
    lessness
    -0.17
    kü
    -0.16
    IDES
    -0.16
    crease
    -0.15
    naments
    -0.15
    gom
    -0.14
    adla
    -0.14
    еÑĩение
    -0.14
    assage
    -0.14
    POSITIVE LOGITS
     enough
    0.37
    ly
    0.32
    ely
    0.31
    ised
    0.29
    izable
    0.28
    ized
    0.27
    iated
    0.25
     indeed
    0.25
    ified
    0.24
     across
    0.24
    Act Density 0.477%

    No Known Activations