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

    Neuronpedia

    INDEX
    Explanations

    selecting specific items or options

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "select" indicating choice or selection processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FORE
    -0.71
    loo
    -0.65
    STD
    -0.63
    naissance
    -0.63
    WARN
    -0.63
    olid
    -0.62
    ovember
    -0.60
    ufact
    -0.59
    peria
    -0.59
    wig
    -0.58
    POSITIVE LOGITS
    ivity
    1.19
    ively
    1.06
    selection
    0.91
    ives
    0.89
    ivities
    0.80
    picked
    0.79
    ive
    0.78
    inations
    0.77
    axe
    0.75
    cuts
    0.75
    Act Density 0.046%

    No Known Activations