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

    Neuronpedia

    INDEX
    Explanations

    phrases related to where people live

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating locations or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¿½
    -0.80
    IJ
    -0.79
    dule
    -0.71
    elli
    -0.69
    opoulos
    -0.68
    Į
    -0.67
    ŃĶ
    -0.66
    omen
    -0.66
    ances
    -0.66
    STAR
    -0.65
    POSITIVE LOGITS
     exile
    0.89
     tents
    0.89
     apartments
    0.86
     poverty
    0.83
     caves
    0.82
     suburb
    0.82
     cramped
    0.81
    hetto
    0.80
     luxury
    0.80
     rented
    0.78
    Act Density 0.116%

    No Known Activations