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

    Neuronpedia

    INDEX
    Explanations

    terms related to absorption in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usakan
    -0.62
    ẵn
    -0.59
     brady
    -0.58
     Desh
    -0.58
    burton
    -0.57
    hbs
    -0.57
     Conley
    -0.56
     Field
    -0.54
    gadier
    -0.54
    euw
    -0.53
    POSITIVE LOGITS
     Absor
    2.07
     absorb
    2.07
     absorbing
    2.02
     absorbs
    1.98
     absorption
    1.94
     absorbed
    1.93
    Absor
    1.92
     Absorption
    1.90
    absorbed
    1.87
     Absorb
    1.81
    Act Density 0.175%

    No Known Activations