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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words representing medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    negative prefixes or terms indicating adversity or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    channelAvailability
    -0.69
     DVDs
    -0.67
     quantity
    -0.66
     breed
    -0.65
     investigators
    -0.65
    uously
    -0.63
     Nurse
    -0.62
     exceptions
    -0.62
     movies
    -0.61
     imitation
    -0.60
    POSITIVE LOGITS
    tur
    1.19
    direction
    1.12
    social
    1.08
    centric
    1.08
    cultural
    1.07
    nom
    1.02
    norm
    1.01
    nuclear
    1.01
    technical
    0.99
    pac
    0.98
    Act Density 0.078%

    No Known Activations