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

    Neuronpedia

    INDEX
    Explanations

    locations or names that begin with "Ch"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "Ch" followed by numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     downhill
    -0.66
     reserved
    -0.66
     bul
    -0.65
     unexplained
    -0.61
     beyond
    -0.60
     constrained
    -0.60
     quotas
    -0.60
     indefinite
    -0.59
     sidel
    -0.59
     abroad
    -0.59
    POSITIVE LOGITS
    ivalry
    1.31
    ieft
    1.29
    ivas
    1.28
    orus
    1.27
    olesterol
    1.26
    atham
    1.22
    ocol
    1.22
    annels
    1.21
    amps
    1.20
    owder
    1.19
    Act Density 0.020%

    No Known Activations