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

    Neuronpedia

    INDEX
    Explanations

    mentions of streets

    oai_token-act-pair · gpt-3.5-turbo

    references to "streets" and related contexts suggesting urban environments or social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emort
    -0.83
    opsis
    -0.77
    itors
    -0.76
    itor
    -0.74
    inite
    -0.73
    essee
    -0.71
    estamp
    -0.71
    iasis
    -0.69
    iotic
    -0.68
    berman
    -0.66
    POSITIVE LOGITS
    cape
    1.20
     streets
    0.99
    fare
    0.94
    walker
    0.87
     sidewalks
    0.85
    ways
    0.84
    walk
    0.80
    wear
    0.79
     sew
    0.77
    ourced
    0.75
    Act Density 0.022%

    No Known Activations