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

    Neuronpedia

    INDEX
    Explanations

    concepts related to being trapped, buried, or enclosed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.95
     Efq
    -0.78
     pleaſure
    -0.77
     perſon
    -0.76
     raiſ
    -0.74
     purpoſe
    -0.72
    perature
    -0.72
     ſta
    -0.71
     reaſon
    -0.71
    ArrowToggle
    -0.70
    POSITIVE LOGITS
     within
    0.70
     behind
    0.65
     inside
    0.63
     firmly
    0.57
     between
    0.56
     in
    0.56
     beneath
    0.55
     tightly
    0.55
     amongst
    0.55
     among
    0.54
    Act Density 0.371%

    No Known Activations