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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing importance or specificity

    oai_token-act-pair · gpt-3.5-turbo

    descriptive words indicating scarcity or minimalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hower
    -0.73
    atcher
    -0.71
    pherd
    -0.68
    acht
    -0.68
    ATURE
    -0.64
    nesday
    -0.64
    SHIP
    -0.64
    Reviewer
    -0.62
    merce
    -0.61
     Cullen
    -0.60
    POSITIVE LOGITS
     regard
    0.88
     intention
    0.83
     impunity
    0.81
     expectation
    0.77
     hindsight
    0.74
     bang
    0.71
     abandon
    0.71
     intentions
    0.71
    standing
    0.71
     intent
    0.71
    Act Density 0.297%

    No Known Activations