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

    Neuronpedia

    INDEX
    Explanations

    references to shells or shell-like structures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ement
    -0.17
    osity
    -0.17
    etta
    -0.16
    ements
    -0.16
    ethe
    -0.16
    este
    -0.16
    oshi
    -0.16
    ettes
    -0.15
    ed
    -0.15
    .bootstrapcdn
    -0.15
    POSITIVE LOGITS
    fish
    0.25
    -shell
    0.22
     shell
    0.22
    shell
    0.21
    mates
    0.20
     Shell
    0.18
    (shell
    0.18
    ãĤº
    0.18
    undy
    0.17
     shells
    0.16
    Act Density 0.018%

    No Known Activations