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

    Neuronpedia

    INDEX
    Explanations

    words related to medical procedures or conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organization and action, especially in a political or social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Immigration
    -0.57
     Opposition
    -0.57
     Fault
    -0.56
     Crimes
    -0.55
     Supporting
    -0.54
     Objective
    -0.54
     Transparency
    -0.54
     Impact
    -0.54
     Imm
    -0.54
     Effective
    -0.53
    POSITIVE LOGITS
    ishly
    0.77
     beetle
    0.67
    xual
    0.61
     extraord
    0.61
     crab
    0.60
    poke
    0.59
     trout
    0.59
    gery
    0.59
     crabs
    0.57
    ldom
    0.57
    Act Density 0.391%

    No Known Activations