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

    Neuronpedia

    INDEX
    Explanations

    terms related to directional movement or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     foglal
    -0.65
     کافی
    -0.57
     kapcs
    -0.55
    legi
    -0.53
    kammer
    -0.52
     kapcsol
    -0.52
     vandens
    -0.51
     kanssa
    -0.51
    fg
    -0.51
     lutte
    -0.50
    POSITIVE LOGITS
    toward
    1.39
     toward
    1.39
    towards
    1.33
     towards
    1.26
     Toward
    1.20
     Towards
    1.18
    Toward
    1.15
    Towards
    1.14
     CreateTagHelper
    1.06
     TOW
    0.96
    Act Density 0.093%

    No Known Activations