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

    Neuronpedia

    INDEX
    Explanations

    words related to sensitivity or resistance to certain factors or stimuli

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to susceptibility or sensitivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uably
    -0.84
    emetery
    -0.80
    ertation
    -0.77
    roy
    -0.76
    lined
    -0.76
    adder
    -0.74
    Registered
    -0.74
    ãģ®éŃĶ
    -0.74
    ridor
    -0.73
    rolled
    -0.71
    POSITIVE LOGITS
     adversity
    0.97
     stimuli
    0.90
     withstand
    0.88
     defend
    0.85
     detecting
    0.85
     fend
    0.84
     ingest
    0.84
     adapting
    0.83
     accommodate
    0.83
     challenge
    0.82
    Act Density 0.128%

    No Known Activations