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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical contact or possession of objects

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to physical interaction or possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arenthood
    -0.60
     anonymity
    -0.58
    VERTISEMENT
    -0.58
     mund
    -0.58
    WARD
    -0.56
    itability
    -0.56
     Presence
    -0.56
    later
    -0.55
     Nebula
    -0.54
    theless
    -0.54
    POSITIVE LOGITS
     dirty
    1.10
     wet
    0.84
     chopped
    0.79
    dirty
    0.76
     Dirty
    0.71
     pumped
    0.68
     blown
    0.68
     rubbed
    0.67
    ivalent
    0.66
     fucked
    0.66
    Act Density 0.058%

    No Known Activations