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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to fear-inducing situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fear or alarming situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cially
    -0.80
    ional
    -0.80
    iciency
    -0.76
     arrang
    -0.68
    ibble
    -0.67
    odore
    -0.65
    tein
    -0.65
     enriched
    -0.64
    iance
    -0.63
    uria
    -0.63
    POSITIVE LOGITS
    crow
    1.81
    mong
    1.42
    warts
    0.94
    cock
    0.82
    vana
    0.79
    wart
    0.77
    inventoryQuantity
    0.75
    Cry
    0.74
    escape
    0.73
    rss
    0.73
    Act Density 0.042%

    No Known Activations