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

    Neuronpedia

    INDEX
    Explanations

    actions related to climbing and ascending

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     downward
    -0.17
    alley
    -0.17
    arme
    -0.15
    anuts
    -0.14
    nero
    -0.14
    éľĩ
    -0.14
    entr
    -0.14
    ipp
    -0.14
    adol
    -0.14
     IonicPage
    -0.14
    POSITIVE LOGITS
     Mount
    0.22
     stairs
    0.22
     ladder
    0.21
     Mt
    0.21
     aboard
    0.20
     Jacob
    0.19
     Jacobs
    0.19
    Jacob
    0.19
     Kil
    0.18
     onto
    0.17
    Act Density 0.020%

    No Known Activations