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

    Neuronpedia

    INDEX
    Explanations

    expressions related to belonging or inclusion

    oai_token-act-pair · gpt-3.5-turbo

    expressions of belonging or inclusion within a group or community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     torped
    -0.72
    gently
    -0.68
     calves
    -0.66
    berus
    -0.65
    stasy
    -0.65
     ceilings
    -0.65
    Recommend
    -0.64
    ricanes
    -0.64
     bolts
    -0.63
     bapt
    -0.63
    POSITIVE LOGITS
    ridge
    0.82
    ICLE
    0.81
    icle
    0.78
    aking
    0.78
    ner
    0.76
    icular
    0.75
    ners
    0.74
    ials
    0.72
    ioned
    0.71
    iator
    0.69
    Act Density 0.031%

    No Known Activations