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

    Neuronpedia

    INDEX
    Explanations

    terms related to versatility and multipurpose use

    oai_token-act-pair · gpt-3.5-turbo

    terms related to design and structural concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inus
    -0.89
    illo
    -0.77
    grave
    -0.74
    KEN
    -0.74
    igers
    -0.73
    atars
    -0.72
     Rosenthal
    -0.72
    href
    -0.71
    angelo
    -0.71
    osaurus
    -0.69
    POSITIVE LOGITS
     solutions
    0.82
     goods
    0.81
     scenarios
    0.79
     versions
    0.78
     packages
    0.76
     items
    0.76
     applications
    0.74
     clothing
    0.74
     options
    0.74
     lifestyles
    0.74
    Act Density 0.194%

    No Known Activations