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

    Neuronpedia

    INDEX
    Explanations

    verbs related to movement or actions in various locations or contexts

    oai_token-act-pair · gpt-3.5-turbo

    actions related to returning home or arriving at a location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    advertising
    -0.67
    obyl
    -0.64
    ranch
    -0.63
    osate
    -0.63
    thood
    -0.62
     Represent
    -0.60
    tain
    -0.59
    phant
    -0.59
    LGBT
    -0.56
    arth
    -0.56
    POSITIVE LOGITS
     promptly
    1.15
     briefly
    1.03
     shortly
    1.03
     afterward
    0.98
     quickly
    0.97
     reluctantly
    0.96
     immediately
    0.94
     calmly
    0.92
     swiftly
    0.91
     later
    0.91
    Act Density 0.680%

    No Known Activations