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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical movement or relocation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    oys
    -0.76
    oured
    -0.74
    iciency
    -0.74
    omial
    -0.69
    inges
    -0.66
    vern
    -0.63
    ificial
    -0.62
    Condition
    -0.60
    cture
    -0.60
    nia
    -0.59
    POSITIVE LOGITS
     toward
    1.15
     towards
    1.14
     forward
    1.14
     away
    1.03
     Forward
    0.89
     into
    0.86
     forwards
    0.86
     closer
    0.84
     Away
    0.81
     onto
    0.81
    Act Density 1.332%

    No Known Activations