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

    Neuronpedia

    INDEX
    Explanations

    references to shells in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Cia
    -0.75
    gadier
    -0.68
    Cia
    -0.68
     Argos
    -0.65
    Bunch
    -0.64
     Silas
    -0.63
    antino
    -0.62
     Tirol
    -0.62
    matic
    -0.61
    lamabad
    -0.61
    POSITIVE LOGITS
     Shell
    1.69
     shells
    1.69
     SHELL
    1.69
     Shells
    1.66
     shell
    1.65
    shell
    1.61
    shells
    1.59
    SHELL
    1.56
    Shell
    1.51
    hells
    1.36
    Act Density 0.024%

    No Known Activations