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

    Neuronpedia

    INDEX
    Explanations

    words related to spy agencies or secret agents

    oai_token-act-pair · gpt-3.5-turbo

    references to agents, particularly in a narrative or investigative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -1.07
    lihood
    -0.95
    etooth
    -0.79
    orld
    -0.77
    ĸļ
    -0.76
    nz
    -0.74
    FACE
    -0.71
    ths
    -0.69
    phrine
    -0.66
    ITCH
    -0.65
    POSITIVE LOGITS
     prov
    0.93
     agent
    0.89
    sov
    0.88
     Agent
    0.88
    agent
    0.85
    agents
    0.81
     agents
    0.80
    illary
    0.76
    ilage
    0.75
     Agents
    0.74
    Act Density 0.026%

    No Known Activations