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

    Neuronpedia

    INDEX
    Explanations

    terms related to volcanic activity and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.04
    2:0.04
    3:0.05
    4:0.07
    5:0.05
    6:0.04
    7:0.32
    8:0.03
    9:0.05
    10:0.05
    11:0.09
    Negative Logits
     Pinball
    -3.22
     Rabbit
    -2.94
     Balloon
    -2.80
     Owl
    -2.68
     Freak
    -2.66
     Robotics
    -2.55
    abbit
    -2.46
     Stab
    -2.43
    Raven
    -2.41
     psychosis
    -2.39
    POSITIVE LOGITS
    IDES
    2.54
    ints
    2.48
    shore
    2.41
    Aff
    2.39
    decl
    2.39
     displ
    2.30
    aff
    2.30
    ess
    2.29
    adh
    2.27
    lys
    2.26
    Act Density 0.002%

    No Known Activations