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

    Neuronpedia

    INDEX
    Explanations

    the word "spe" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baugh
    -0.16
    rip
    -0.15
    InstanceId
    -0.15
    antine
    -0.15
    oust
    -0.15
    nf
    -0.14
    lyn
    -0.14
    osp
    -0.14
    ned
    -0.14
    nees
    -0.14
    POSITIVE LOGITS
     spe
    0.23
    aking
    0.21
    ake
    0.20
    akers
    0.20
     Spe
    0.20
    -spe
    0.18
    Spe
    0.17
    IFIC
    0.17
    iment
    0.17
    ktor
    0.17
    Act Density 0.006%

    No Known Activations