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

    Neuronpedia

    INDEX
    Explanations

    phrases related to returning or going back to a particular place or role

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a return to a specific location or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.76
     conveyed
    -0.66
    SourceFile
    -0.65
    ihad
    -0.64
     gone
    -0.64
    holes
    -0.61
    VPN
    -0.61
    Mah
    -0.60
    erity
    -0.60
     precursor
    -0.59
    POSITIVE LOGITS
     haunt
    1.16
     shore
    0.92
     grips
    0.79
     fold
    0.78
     pasture
    0.78
     shores
    0.78
     prominence
    0.75
     fray
    0.75
     earth
    0.74
     Earth
    0.71
    Act Density 0.058%

    No Known Activations