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

    Neuronpedia

    INDEX
    Explanations

    phrases related to paving the way for future events or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causal relationships or pathways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.75
    ãĥij
    -0.75
    heart
    -0.72
    çī
    -0.70
    CV
    -0.69
    ãĥ¼ãĤ¯
    -0.68
    hai
    -0.65
    jab
    -0.65
    ãĤ¼
    -0.64
    cles
    -0.63
    POSITIVE LOGITS
    geries
    0.89
     eventual
    0.82
     experimentation
    0.82
    gery
    0.79
     disaster
    0.77
     negotiations
    0.76
    bidden
    0.74
     future
    0.74
     impeachment
    0.69
    icial
    0.69
    Act Density 0.162%

    No Known Activations