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

    Neuronpedia

    INDEX
    Explanations

    phrases related to experiences and interactions over time

    oai_token-act-pair · gpt-3.5-turbo

    references to years of experience and contributions in a collaborative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ives
    -0.65
    eness
    -0.64
    cock
    -0.62
    orescence
    -0.60
    ariat
    -0.57
    tumblr
    -0.57
    nikov
    -0.55
    verett
    -0.55
    iquid
    -0.55
    hoe
    -0.54
    POSITIVE LOGITS
     viz
    0.72
    é¾įå¥ij士
    0.69
     ancestors
    0.60
    )]
    0.60
    luster
    0.59
     previous
    0.59
     predecessors
    0.57
     kitchens
    0.57
     occasions
    0.57
     prior
    0.57
    Act Density 0.912%

    No Known Activations