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

    Neuronpedia

    INDEX
    Explanations

    verbs related to giving directions or guidance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to teaching and instruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vow
    -0.63
     Roses
    -0.63
     Bok
    -0.63
     bomber
    -0.62
    oner
    -0.62
    buster
    -0.60
    cube
    -0.58
    fare
    -0.57
     á
    -0.57
     Scotia
    -0.57
    POSITIVE LOGITS
    acebook
    0.95
    yrinth
    0.89
    htaking
    0.83
     instruct
    0.82
    ments
    0.81
    ision
    0.79
    eering
    0.77
     certific
    0.76
    uable
    0.75
    ussen
    0.75
    Act Density 0.027%

    No Known Activations