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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or progression from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sequence or reference to previous information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eers
    -0.69
    HH
    -0.66
    aah
    -0.66
     Bundy
    -0.65
    %%%%
    -0.64
     Nationals
    -0.61
    rongh
    -0.61
    YES
    -0.60
     Zin
    -0.60
    natureconservancy
    -0.59
    POSITIVE LOGITS
     onwards
    1.26
     onward
    1.15
    forward
    0.80
    idate
    0.76
    annis
    0.76
     sprang
    0.75
    forth
    0.72
    oded
    0.72
    iral
    0.71
    awaru
    0.69
    Act Density 0.041%

    No Known Activations