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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly the names of individuals and associated characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chem
    -0.65
     womb
    -0.62
     Mandatory
    -0.60
     CTR
    -0.60
    HQ
    -0.59
     AAC
    -0.59
     imprint
    -0.59
    ModLoader
    -0.58
     MDMA
    -0.58
    ankind
    -0.58
    POSITIVE LOGITS
     apologised
    0.87
    arde
    0.82
    igl
    0.81
    chin
    0.78
    cott
    0.78
    itsch
    0.78
    iewicz
    0.76
    ichick
    0.76
    zinski
    0.76
    acker
    0.73
    Act Density 0.131%

    No Known Activations