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

    Neuronpedia

    INDEX
    Explanations

    phrases related to showing or demonstrating something to someone

    oai_token-act-pair · gpt-3.5-turbo

    references to characters or people being shown or introduced in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anxiety
    -0.68
    semble
    -0.68
     Carrie
    -0.64
    semb
    -0.63
    ente
    -0.62
     Centers
    -0.62
    iston
    -0.61
     impact
    -0.59
     stopp
    -0.59
     cluster
    -0.59
    POSITIVE LOGITS
    selves
    0.73
    rov
    0.70
    ov
    0.68
    aught
    0.67
    âĸij
    0.67
    self
    0.66
    aeper
    0.66
    arov
    0.65
    flix
    0.65
    owitz
    0.65
    Act Density 0.080%

    No Known Activations