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

    Neuronpedia

    INDEX
    Explanations

    words related to progress or changing state, often focused on negative outcomes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "get" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    velt
    -0.74
    iege
    -0.65
    amiya
    -0.60
     Britann
    -0.60
    ively
    -0.60
     Archdemon
    -0.58
     Examiner
    -0.58
     depiction
    -0.57
     Madness
    -0.57
    orney
    -0.56
    POSITIVE LOGITS
     rid
    1.21
    cloneembedreportprint
    0.93
    tin
    0.87
    ãĥ³ãĤ¸
    0.81
    TING
    0.80
     progressively
    0.78
     underway
    0.77
     sucked
    0.75
    aways
    0.74
    away
    0.74
    Act Density 0.135%

    No Known Activations