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

    Neuronpedia

    INDEX
    Explanations

    words related to theft and robbery

    oai_token-act-pair · gpt-3.5-turbo

    terms related to theft and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Matters
    -0.69
    VR
    -0.65
     Veter
    -0.64
    ANA
    -0.64
     Pradesh
    -0.63
     unification
    -0.63
     increments
    -0.63
    Recommend
    -0.62
    Relations
    -0.61
     Presence
    -0.60
    POSITIVE LOGITS
     beware
    1.08
     thieves
    0.94
     prey
    0.93
     thief
    0.87
     deceived
    0.87
     who
    0.86
     cheated
    0.84
     smugglers
    0.83
     trespass
    0.80
     smugg
    0.78
    Act Density 0.051%

    No Known Activations