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

    Neuronpedia

    INDEX
    Explanations

    words related to imminent threats or important issues that are approaching

    oai_token-act-pair · gpt-3.5-turbo

    references to impending situations or threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ive
    -0.82
    hib
    -0.82
    hibition
    -0.80
    ilic
    -0.80
    verts
    -0.78
    ives
    -0.78
    ves
    -0.77
    ilar
    -0.74
    uties
    -0.73
    expression
    -0.72
    POSITIVE LOGITS
     omin
    1.04
     looms
    1.02
     looming
    0.87
    abouts
    0.85
     Pose
    0.77
     suspic
    0.72
     eclips
    0.72
     silhou
    0.71
     dusk
    0.70
     inev
    0.70
    Act Density 0.020%

    No Known Activations