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

    Neuronpedia

    INDEX
    Explanations

    phrases related to future plans or upcoming events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "next" associated with various contexts or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lees
    -0.81
    enance
    -0.76
     Coulter
    -0.72
    rs
    -0.72
    hes
    -0.71
    theless
    -0.68
    ocker
    -0.67
    icone
    -0.67
    adow
    -0.67
     Lauder
    -0.67
    POSITIVE LOGITS
     generation
    1.08
     iteration
    0.97
     installment
    0.97
     generations
    0.94
     incarnation
    0.92
     occupant
    0.92
     step
    0.90
     decade
    0.87
     crop
    0.87
     phase
    0.87
    Act Density 0.035%

    No Known Activations