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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software installation and manipulation

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to software installation and configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lasted
    -0.79
     unborn
    -0.71
     portrays
    -0.70
    edo
    -0.69
    otype
    -0.69
    ensable
    -0.66
    ghazi
    -0.65
     overshadowed
    -0.64
     worshipped
    -0.63
    stadt
    -0.62
    POSITIVE LOGITS
     manually
    0.81
     manual
    0.77
     either
    0.75
    Alternatively
    0.72
     clicks
    0.71
     zip
    0.69
     ILCS
    0.69
    CHO
    0.68
     flick
    0.67
     simple
    0.67
    Act Density 0.337%

    No Known Activations