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

    Neuronpedia

    INDEX
    Explanations

    phrases related to abstract concepts such as principles and structures

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to physical attributes and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suspended
    -0.60
     Badge
    -0.58
     corrid
    -0.58
    iann
    -0.56
     Jagu
    -0.55
    pard
    -0.55
     Panthers
    -0.55
     digitally
    -0.54
    approved
    -0.54
     Jem
    -0.53
    POSITIVE LOGITS
    Reviewer
    0.76
     but
    0.71
     proportions
    0.69
     sake
    0.68
     comparisons
    0.68
     insofar
    0.66
    yet
    0.66
    arist
    0.65
    smanship
    0.64
     due
    0.63
    Act Density 0.429%

    No Known Activations