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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to signing up for newsletters and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tains
    -0.76
     Franç
    -0.68
    ibaba
    -0.68
     loft
    -0.65
     kindly
    -0.65
     brill
    -0.65
     shine
    -0.65
     Hann
    -0.63
    etheless
    -0.62
    ibilities
    -0.62
    POSITIVE LOGITS
    Cola
    0.76
    Newsletter
    0.69
     TAMADRA
    0.68
     newsletters
    0.66
    entimes
    0.65
     Newsletter
    0.64
    $$$$
    0.63
    Tell
    0.63
    OS
    0.62
     newsletter
    0.61
    Act Density 0.057%

    No Known Activations