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

    Neuronpedia

    INDEX
    Explanations

    references to offices and office-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osomal
    -0.59
    /*
    -0.59
    ISupport
    -0.59
    //
    -0.57
     Tamara
    -0.55
    ratos
    -0.54
     iVar
    -0.54
    printk
    -0.53
    accro
    -0.52
     Vor
    -0.51
    POSITIVE LOGITS
     offices
    0.99
     office
    0.84
     headquarters
    0.73
     jail
    0.69
     oficina
    0.66
     SIMBAD
    0.65
     oficinas
    0.65
     obligado
    0.64
    offices
    0.63
     Jail
    0.62
    Act Density 0.068%

    No Known Activations