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

    Neuronpedia

    INDEX
    Explanations

    mentions of mutant powers and their implications in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Maryland
    -0.18
     Baltimore
    -0.17
    cak
    -0.16
     Gong
    -0.16
    cid
    -0.15
    dummy
    -0.15
    ejs
    -0.15
    onta
    -0.14
     Orioles
    -0.14
     Camden
    -0.14
    POSITIVE LOGITS
     mutants
    0.29
     mutant
    0.29
     Wolverine
    0.25
     Mut
    0.24
     Xavier
    0.23
     mutation
    0.22
    mut
    0.22
     Mutation
    0.21
     MUT
    0.20
    Mut
    0.20
    Act Density 0.021%

    No Known Activations