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

    Neuronpedia

    INDEX
    Explanations

    instances of statements or situations with a strong emotional impact

    oai_token-act-pair · gpt-3.5-turbo

    prominent adjectives that convey significance or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     safely
    -0.65
    iphate
    -0.64
     Rohingya
    -0.63
    ntil
    -0.62
    gettable
    -0.62
    iasco
    -0.61
     Chargers
    -0.61
    icipated
    -0.61
     persecuted
    -0.59
     stoked
    -0.59
    POSITIVE LOGITS
     proportions
    0.75
     mode
    0.72
    oru
    0.69
    history
    0.68
     origin
    0.68
    mia
    0.66
    thia
    0.65
     circumstances
    0.65
     ausp
    0.63
    credit
    0.62
    Act Density 0.463%

    No Known Activations