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

    Neuronpedia

    INDEX
    Explanations

    phrases related to newsletters and subscription actions

    oai_token-act-pair · gpt-3.5-turbo

    references to personal or direct communication with the audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.77
    itialized
    -0.69
    nesota
    -0.69
    JUST
    -0.63
    hift
    -0.63
    amac
    -0.62
    isson
    -0.61
     Hung
    -0.60
    imil
    -0.59
    icion
    -0.58
    POSITIVE LOGITS
    unes
    0.71
    abba
    0.67
    atics
    0.66
     cheaply
    0.64
     Apply
    0.62
     Crate
    0.62
    atic
    0.61
     princip
    0.61
    adow
    0.61
     {{
    0.60
    Act Density 0.069%

    No Known Activations