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

    Neuronpedia

    INDEX
    Explanations

    phrases pertaining to planning and future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.65
     endwhile
    -0.53
     therein
    -0.51
    verket
    -0.51
    atschappij
    -0.49
    Билгалдахарш
    -0.49
     entrando
    -0.49
     newItem
    -0.49
    OGND
    -0.47
     Walking
    -0.47
    POSITIVE LOGITS
     headed
    1.42
     head
    1.30
    headed
    1.23
     heads
    1.16
     HEAD
    1.10
    Head
    1.07
    head
    1.06
     heading
    1.06
     Head
    1.04
    HEAD
    1.03
    Act Density 0.266%

    No Known Activations