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

    Neuronpedia

    INDEX
    Explanations

    references to climbing or ascending actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alley
    -0.16
    ikel
    -0.16
    éĹ´
    -0.15
    opers
    -0.15
    éĸĵ
    -0.15
    935
    -0.15
    arme
    -0.14
    éľĩ
    -0.14
     downward
    -0.14
    ursors
    -0.14
    POSITIVE LOGITS
     stairs
    0.20
     onto
    0.19
     Mount
    0.18
     climb
    0.18
     Mt
    0.18
     ladder
    0.17
     aboard
    0.17
    onto
    0.17
    aine
    0.17
     into
    0.17
    Act Density 0.016%

    No Known Activations