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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation and recognition towards others

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disrupting
    -0.71
    scape
    -0.67
     prototypes
    -0.67
     nightmares
    -0.66
     disrupted
    -0.64
     photographed
    -0.63
     headlines
    -0.63
     indoors
    -0.63
     disruptive
    -0.63
     overnight
    -0.62
    POSITIVE LOGITS
     bestowed
    0.81
    udos
    0.75
    nat
    0.73
    entin
    0.72
    enza
    0.71
    edi
    0.71
    llah
    0.69
    ends
    0.67
     Cosponsors
    0.67
     Towards
    0.67
    Act Density 0.245%

    No Known Activations