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

    Neuronpedia

    INDEX
    Explanations

    words related to illegal activities, particularly financial crimes

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of plundering or exploiting resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    relevant
    -0.63
     awake
    -0.60
     avail
    -0.59
    Ö¼
    -0.58
     PAL
    -0.56
     Sabha
    -0.55
     multiplying
    -0.55
     sleeper
    -0.55
     "$:/
    -0.54
     aback
    -0.54
    POSITIVE LOGITS
    encia
    1.03
    ocene
    0.98
    inational
    0.87
    emouth
    0.83
    ued
    0.82
    estyles
    0.82
    erers
    0.81
    iar
    0.78
    hetto
    0.76
    viks
    0.75
    Act Density 0.057%

    No Known Activations