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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditions and considerations in a variety of practical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ais
    -0.15
     internal
    -0.15
    bite
    -0.14
    lich
    -0.14
    age
    -0.14
    mia
    -0.14
    ays
    -0.14
     entire
    -0.13
     various
    -0.13
     remaining
    -0.13
    POSITIVE LOGITS
    ensitive
    0.22
     sensitive
    0.21
    -sensitive
    0.20
    Sensitive
    0.18
     susceptible
    0.18
     delicate
    0.17
    -heavy
    0.17
    oire
    0.16
     suscept
    0.16
    æ¶ī
    0.15
    Act Density 0.164%

    No Known Activations