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

    Neuronpedia

    INDEX
    Explanations

    names of politicians

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "being."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     camps
    -0.69
     dead
    -0.64
     Dep
    -0.63
     deleg
    -0.62
     vanquished
    -0.62
     wards
    -0.62
     houses
    -0.61
     archae
    -0.61
     casualties
    -0.60
     sponsors
    -0.60
    POSITIVE LOGITS
    ibe
    4.73
    ib
    1.54
    ibo
    1.32
    ibel
    1.19
    ibble
    1.15
    ibur
    1.15
    ibr
    1.09
    iber
    1.07
    ibia
    1.02
    ivo
    1.02
    Act Density 0.012%

    No Known Activations