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

    Neuronpedia

    INDEX
    Explanations

    phrases related to email subscription attempts

    oai_token-act-pair · gpt-3.5-turbo

    the word "Could" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Skydragon
    -0.72
    vance
    -0.64
    hips
    -0.63
    SPONSORED
    -0.62
    ostic
    -0.62
    lier
    -0.61
    anders
    -0.60
    core
    -0.60
    folk
    -0.60
    ollower
    -0.58
    POSITIVE LOGITS
    berra
    0.84
     conce
    0.81
    avascript
    0.79
     feas
    0.75
    adian
    0.70
     mistake
    0.70
    nel
    0.69
    prus
    0.69
     hypot
    0.68
     conflic
    0.68
    Act Density 0.031%

    No Known Activations