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

    Neuronpedia

    INDEX
    Explanations

    instances of people leaving and returning to a place or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "return" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vern
    -0.75
    ahi
    -0.73
    hemat
    -0.69
    cape
    -0.68
    Cola
    -0.67
    boss
    -0.65
    hest
    -0.65
    odan
    -0.64
    chen
    -0.63
    acht
    -0.63
    POSITIVE LOGITS
     home
    0.87
    ees
    0.83
     HOME
    0.80
    home
    0.79
     Returning
    0.74
     postage
    0.70
     Home
    0.69
    zl
    0.68
    porting
    0.68
    owship
    0.67
    Act Density 0.030%

    No Known Activations