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

    Neuronpedia

    INDEX
    Explanations

    actions and activities related to climbing and movement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ²
    -0.17
     bulld
    -0.16
    pressor
    -0.15
    åĿ¦
    -0.15
    illez
    -0.15
    ãĥ¡ãĥ³ãĥĪ
    -0.15
    ubit
    -0.15
     GenerationType
    -0.14
     fronts
    -0.14
     Bulld
    -0.14
    POSITIVE LOGITS
     tree
    0.26
     suspended
    0.24
     climbing
    0.24
     hanging
    0.23
     climb
    0.23
     tower
    0.23
     prec
    0.22
    tree
    0.22
     hung
    0.21
     Tree
    0.21
    Act Density 0.176%

    No Known Activations