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

    Neuronpedia

    INDEX
    Explanations

    words related to choices or options

    oai_token-act-pair · gpt-3.5-turbo

    the word "or" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     horizont
    -0.72
    onday
    -0.67
    elong
    -0.65
    Dear
    -0.63
    ilton
    -0.61
    achine
    -0.60
    idem
    -0.60
    opian
    -0.59
    pter
    -0.59
    agra
    -0.59
    POSITIVE LOGITS
    acles
    1.30
    acle
    1.27
    chard
    1.27
    Else
    1.26
    lando
    1.13
    chid
    1.11
    acular
    1.08
    ifice
    1.05
    nam
    1.05
    ific
    1.02
    Act Density 0.107%

    No Known Activations