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

    Neuronpedia

    INDEX
    Explanations

    phrases related to deep foundational principles or causes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to being established or having a foundational basis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.76
    tein
    -0.73
     MARK
    -0.68
    emies
    -0.67
    chief
    -0.66
    ctic
    -0.65
    pmwiki
    -0.64
    airs
    -0.63
    nesota
    -0.62
    otos
    -0.62
    POSITIVE LOGITS
     rooted
    0.97
     rooting
    0.75
    kit
    0.71
    SourceFile
    0.69
     embedded
    0.68
     behind
    0.66
     oper
    0.63
     milit
    0.62
     anchored
    0.62
     corrid
    0.61
    Act Density 0.005%

    No Known Activations